论文检索

Applications · Language, Speech and Dialog

Jessy Lin, Vincent-Pierre Berges, Xilun Chen, Scott Yih, Gargi Ghosh, Barlas Oguz

LLMs are known to store vast amounts of knowledge in their parametric memory. However, learning and recalling facts from this memory is known to be unreliable, depending largely on the prevalence of particular facts in the training data and other factors which are poorly understood. Practitioners are lacking tools which will allow them to ensure that the models learn a given body of knowledge reliably and consistently. To this end, we propose Active Reading: a framework where we train models to study a given set of material with self-generated learning strategies. First, we demonstrate models trained with Active Reading on expert domains absorb significantly more knowledge than vanilla finetuning and other data augmentations. We train expert 8B models that achieve 66% on a Wikipedia-grounded subset of SimpleQA (+313% relative over vanilla finetuning) and 26% on FinanceBench (+160% relative over vanilla finetuning) by applying Active Reading to the source documents for each benchmark. Finally, we show that Active Reading can be utilized at pre-training scale to build more factual models. As a demonstration of this, we release WikiExpert-8B, a Wikipedia-expert model trained on 1 trillion generated tokens, which outcompetes models with hundreds of billions of parameters on factual QA.

Applications · Language, Speech and Dialog

Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Setlur, Russ Salakhutdinov, Chelsea Finn, Aviral Kumar

Reasoning requires going beyond pattern matching or memorization of solutions to identify and implement algorithmic procedures that can be used to deduce answers to hard problems. Doing so requires reusing primitives, intermediate results, or procedures across multiple problems. While RL post-training on long chains of thought ultimately aims to uncover this kind of algorithmic behavior, the depth-first and brute-force nature of reasoning traces learned by these models suggests that this is far from a fulfilled promise. To address more effective reasoning, we introduce reasoning abstractions: concise natural language descriptions of procedural and factual knowledge that guide the model toward learning successful reasoning. We train models to be capable of proposing several useful abstractions given a problem, followed by RL training that incentivizes building a solution while using the information provided by these abstractions. This results in a two-player RL training paradigm, abbreviated as RLAD, that jointly trains an abstraction generator and an abstraction-conditioned solution generator. This setup effectively enables structured exploration, decouples learning signals of abstraction proposal and solution generation, and improves generalization to harder problems. We also show that spending more test-time compute into generating abstractions is more beneficial for performance than generating more solutions at large inference-time budgets, illustrating the role of abstractions in guiding global exploration.

Reinforcement Learning · Batch/Offline

Pragya Srivastava, Harman Singh, Rahul Madhavan, Gandharv Patil, Sravanti Addepalli, Arun Suggala, Rengarajan Aravamudhan, Soumya Sharma, Anirban Laha, Aravindan Raghuveer 等

Reward models (RMs) are fundamental to aligning Large Language Models (LLMs) via human feedback, yet they often suffer from reward hacking. They tend to latch on to superficial or spurious attributes, such as response length or formatting, mistaking these cues learned from correlations in training data for the true causal drivers of quality (e.g., factuality, relevance). This occurs because standard training objectives struggle to disentangle these factors, leading to brittle RMs and misaligned policies. We introduce CROME (Causally Robust Reward Modeling), a novel framework inspired by an explicit causal model designed to mitigate reward hacking. CROME queries an oracle LLM for rubrics that are (or the oracle deems to be) causally relevant to answering a specific prompt. Then, it employs the following synthetic targeted augmentations during training: (1) Causal Augmentations, which are pairs that differ along specific causal attributes (subset of the Oracle identified rubrics), to enforce sensitivity along each causal attribute individually, and (2) Neutral Augmentations, which are tie-label pairs varying primarily in spurious attributes, to enforce invariance along spurious attributes. Notably, our neutral augmentations are produced without any knowledge of unknown spurious factors, via question swapping and response interventions only along causal rubrics. We show that the CROME augmentation strategy using rubrics from popular LLM APIs significantly outperforms standard baselines on RewardBench, improving average accuracy by up to 5.3% and achieving gains of up to 7.1% and 12.4% in reasoning and safety. The robustness of CROME is further testified by significant gains in DPO-aligned policies and Best-of-N alignment across various benchmarks, including AlpacaEval 2.0, RewardBench, safety-focused WildGuardTest, and the reasoning-specific GSM8k.

Reinforcement Learning · Deep RL

Ezgi Korkmaz

Learning in high-dimensional MDPs with complex state dynamics became possible with the progress achieved in reinforcement learning research. At the same time, deep neural policies have been observed to be highly unstable with respect to the minor variations in their state space, causing volatile and unpredictable behaviour. To alleviate these volatilities, a line of work suggested techniques to cope with this problem via explicitly regularizing the temporal difference loss to ensure local $\epsilon$-invariance in the state space. In this paper, we provide theoretical foundations on the impact of robust, i.e. adversarial, training on reinforcement learning. Our comprehensive theoretical and experimental analysis reveals that standard reinforcement learning inherently learns counterfactual values while recent training techniques that focus on explicitly enforcing $\epsilon$-local invariance cause policies to lose counterfactuality, and further result in learning misaligned and inconsistent values. In connection to this analysis, we further highlight that this line of training methods breaks the core intuition and the true biological inspiration of reinforcement learning, sacrifices essential inherent skills that enable reasoning and generalization, and introduces an intrinsic gap between how natural intelligence understands and interacts with an environment in contrast to AI agents trained via $\epsilon$-local invariance methods. The misalignment, inaccuracy and the loss of counterfactuality revealed in our paper further demonstrate the need to rethink the approach in establishing truly reliable and generalizable reinforcement learning policies.

Applications · Language, Speech and Dialog

Pranav Narayanan Venkit, Philippe Laban, Yilun Zhou, Kung-Hsiang Huang, Yixin Mao, Chien-Sheng Wu

Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce _DeepTRACE_, a novel sociotechnically grounded audit framework that turns prior community-identified failure cases into eight measurable dimensions spanning answer text, sources, and citations. DeepTRACE uses statement-level analysis (decomposition, confidence scoring) and builds citation and factual-support matrices to audit how systems reason with and attribute evidence end-to-end. Using automated extraction pipelines for popular public models (e.g., GPT-4.5/5, You.com, Perplexity, Copilot/Bing, Gemini) and an LLM-judge with validated agreement to human raters, we evaluate both web-search engines and deep-research configurations. Our findings show that generative search engines and deep research agents frequently produce one-sided, highly confident responses on debate queries and include large fractions of statements unsupported by their own listed sources. Deep-research configurations reduce overconfidence and can attain high citation thoroughness, but they remain highly one-sided on debate queries and still exhibit large fractions of unsupported statements, with citation accuracy ranging from 40–80\% across systems. Unlike prior factuality and citation metrics that focus on claim correctness or academic summarization, DeepTRACE audits end-to-end GSE/DR behavior, including citation necessity, unsupported-statement rates, and URL-level citation structure.

Applications · Language, Speech and Dialog

Weixuan Wang, Minghao Wu, Barry Haddow, Alexandra Birch

Long document summarization remains a significant challenge for current large language models (LLMs), as existing approaches commonly struggle with information loss, factual inconsistencies, and coherence issues when processing excessively long documents. We propose SummQ, a novel adversarial multi-agent framework that addresses these limitations through collaborative intelligence between specialized agents operating in two complementary domains: summarization and quizzing. Our approach employs summary generators and reviewers that work collaboratively to create and evaluate comprehensive summaries, while quiz generators and reviewers create comprehension questions that serve as continuous quality checks for the summarization process. This adversarial dynamic, enhanced by an examinee agent that validates whether the generated summary contains the information needed to answer the quiz questions, enables iterative refinement through multifaceted feedback mechanisms. We evaluate SummQ on three widely used long document summarization benchmarks. Experimental results demonstrate that our framework significantly outperforms existing state-of-the-art methods across ROUGE and BERTScore metrics, as well as in LLM-as-a-Judge and human evaluations. Our comprehensive analyses reveal the effectiveness of the multi-agent collaboration dynamics, the influence of different agent configurations, and the impact of the quizzing mechanism. This work establishes a new approach for long document summarization that uses adversarial agentic collaboration to improve summarization quality.

Social Aspects · Trustworthy Machine Learning

Zirui Hu, Zheng Zhang, Yingjie Wang, Leszek Rutkowski, Dacheng Tao

Large Language Models (LLMs) excel in natural language processing (NLP) tasks but often generate false or misleading information, known as hallucinations, raising reliability concerns in high-stakes applications. To provide statistical guarantees on the factuality of LLM outputs, conformal prediction based techniques have been proposed. Despite their strong theoretical guarantees, they rely heavily on the exchangeability assumption between calibration and test data, which is frequently violated in real-world scenarios with dynamic covariate shifts. To overcome this limitation, we introduce \textbf{CoFact}, a conformal prediction framework that uses online density ratio estimation to adaptively reweigh calibration data, ensuring alignment with evolving test distributions. With this approach, CoFact bypasses the exchangeability requirement and provides robust factuality guarantees under non-stationary conditions. To theoretically justify CoFact, we establish an upper bound on the gap between the actual hallucination rate and the target level $\alpha$, demonstrating that the bound asymptotically approaches zero as the number of rounds and calibration samples increase. Empirically, CoFact is evaluated on MedLFQA, WikiData, and the newly introduced \textbf{WildChat+} dataset, which captures real-world covariate shifts through user-generated prompts. Results demonstrate that CoFact consistently outperforms existing methods, maintaining reliability even under dynamic conditions.

Social Aspects · Trustworthy Machine Learning

Guangzhi Xiong, Zhenghao He, Bohan Liu, Sanchit Sinha, Aidong Zhang

Retrieval-Augmented Generation (RAG) improves the factuality of large language models (LLMs) by grounding outputs in retrieved evidence, but faithfulness failures, where generations contradict or extend beyond the provided sources, remain a critical challenge. Existing hallucination detection methods for RAG often rely either on large-scale detector training, which requires substantial annotated data, or on querying external LLM judges, which leads to high inference costs. Although some approaches attempt to leverage internal representations of LLMs for hallucination detection, their accuracy remains limited. Motivated by recent advances in mechanistic interpretability, we employ sparse autoencoders (SAEs) to disentangle internal activations, successfully identifying features that are specifically triggered during RAG hallucinations. Building on a systematic pipeline of information-based feature selection and additive feature modeling, we introduce RAGLens, a lightweight hallucination detector that accurately flags unfaithful RAG outputs using LLM internal representations. RAGLens not only achieves superior detection performance compared to existing methods, but also provides interpretable rationales for its decisions, enabling effective post-hoc mitigation of unfaithful RAG. Finally, we justify our design choices and reveal new insights into the distribution of hallucination-related signals within LLMs. The code is available at https://github.com/Teddy-XiongGZ/RAGLens.

Social Aspects · Accountability, Transparency and Interpretability

Jingtong Su, Julia Kempe, Karen Ullrich

Transformers have achieved state-of-the-art performance across diverse language and vision tasks. This success drives the imperative to interpret their internal mechanisms with the dual goals of enhancing performance and improving behavioral control. Attribution methods help advance interpretability by assigning model outputs associated with a target concept to specific model components. Current attribution research primarily studies multi-layer perceptron (MLP) neurons and addresses relatively simple concepts such as factual associations (e.g., Paris is located in France). This focus tends to overlook the impact of the attention mechanism and lacks a unified approach for analyzing more complex concepts. To fill these gaps, we introduce Scalable Attention Module Discovery (SAMD), a concept-agnostic method for mapping arbitrary, complex concepts to specific attention heads of general transformer models. We accomplish this by representing each concept as a vector, calculating its cosine similarity with each attention head, and selecting the TopK-scoring heads to construct the concept-associated attention module. We then propose Scalar Attention Module Intervention (SAMI), a simple strategy to diminish or amplify the effects of a concept by adjusting the attention module using only a single scalar parameter. Empirically, we demonstrate SAMD on concepts of varying complexity, and visualize the locations of their corresponding modules. Our results demonstrate that module locations remain stable before and after LLM post-training, and confirm prior work on the mechanics of LLM multi-lingualism. Through SAMI, we facilitate jailbreaking on HarmBench (+72.7%) by diminishing “safety” and improve performance on the GSM8K benchmark (+1.6%) by amplifying “reasoning”. Lastly, we highlight the domain-agnostic nature of our approach by suppressing the image classification accuracy of vision transformers on ImageNet.

Social Aspects · Fairness, Equity, Justice and Safety

Junxiao Yang, Jinzhe Tu, Haoran Liu, Xiaoce Wang, Chujie Zheng, Zhexin Zhang, Shiyao Cui, Caishun Chen, Tiantian He, Hongning Wang 等

Recent advances in Large Reasoning Models (LRMs) have shown impressive capabilities in mathematical and logical reasoning. However, current LRMs rarely admit ignorance or respond with “I don’t know”. Instead, they often produce incorrect answers while showing undue confidence, raising concerns about their factual reliability. In this work, we identify two pathological reasoning patterns characterized by overthinking that contribute to the overconfident and incorrect answers: last-minute guessing and second-thought spiraling. To address these issues, we propose BARREL—a novel framework that promotes concise and boundary-aware factual reasoning. Our experiments show that BARREL-training increases the reliability of DeepSeek-R1-Distill-Llama-8B from 39.33% to 61.48%, while still achieving accuracy comparable to models finetuned on reasoning data generated by R1. These results demonstrate that our pilot study is inspiring to build more reliable and factual System 2 LRMs.

Social Aspects · Trustworthy Machine Learning

Saleh Zare Zade, Xiangyu Zhou, Sijia Liu, Dongxiao Zhu

Large Language Models are prone to memorizing sensitive, copyrighted, or hazardous content, posing significant privacy and legal concerns. Retraining from scratch is computationally infeasible, whereas current unlearning methods exhibit unstable trade-offs between forgetting and utility, frequently producing incoherent outputs on forget prompts and failing to generalize due to the persistence of lexical-level and semantic-level associations in attention. We propose Attention Smoothing Unlearning (ASU), a principled framework that casts unlearning as self-distillation from a forget-teacher derived from the model’s own attention. By increasing the softmax temperature, ASU flattens attention distributions and directly suppresses the lexical-level and semantic-level associations responsible for reconstructing memorized knowledge. This results in a bounded optimization objective that erases factual information yet maintains coherence in responses to forget prompts. Empirical evaluation on TOFU, MUSE, and WMDP, along with real-world and continual unlearning scenarios across question answering and text completion, demonstrates that ASU outperforms the baselines for most of the unlearning scenarios, delivering robust unlearning with minimal loss of model utility.

General Machine Learning · Representation Learning

Paul Youssef, Zhixue Zhao, Christin Seifert, Jörg Schlötterer

Knowledge editing methods (KEs) are a cost-effective way to update the factual content of large language models (LLMs), but they pose a dual-use risk. While KEs are beneficial for updating outdated or incorrect information, they can be exploited maliciously to implant misinformation or bias. In order to defend against these types of malicious manipulation, we need robust techniques that can reliably detect, interpret, and mitigate malicious edits. To that end, we introduce the tasks of tracing and reversing edits. We propose a novel method to infer the edited object entity, solely based on the modified weights, without access to the editing prompt or any other semantically similar prompts, with up to 99\% accuracy. Further, we propose an effective and training-free method for reversing edits. Our method reverses up to 94\% of the edits, and helps regain the original model's output distribution without access to any information about the edit. This method can further be repurposed to distinguish between edited and unedited weights. Our findings highlight the feasibility of tracing and reversing edits based on the edited weights, opening a new research direction for safeguarding LLMs against adversarial manipulations.

Applications · Language, Speech and Dialog

Thinh Pham, Nguyen Nguyen, Pratibha Zunjare, Weiyuan Chen, Yu-Min Tseng, Tu Vu

We introduce SealQA, a challenge benchmark for evaluating SEarch-Augmented Language models on fact-seeking questions where web search yields conflicting, noisy, or unhelpful results. SealQA comes in three flavors: (1) SEAL-0 (main) and (2) SEAL-HARD, both of which assess factual accuracy and reasoning capabilities, where SEAL-0 targets the most challenging questions that frontier non-reasoning models (e.g., GPT-4.1) answer with near-zero accuracy; and (3) LongSeal, which extends SealQA to test long-context, multi-document reasoning in "needle-in-a-haystack" settings. Our evaluation reveals critical limitations in current models. Even frontier reasoning models face significant challenges across SealQA flavors. On SEAL-0, GPT-5 with tools achieves only 43.2% accuracy at its best reasoning effort. We also find that even advanced reasoning models (e.g., DeepSeek-R1) can be vulnerable to noisy search results. Notably, increasing test-time compute does not yield reliable gains across GPT-5 and the o-series of models, with performance often plateauing or even declining early. Finally, while current models are less affected by the "lost-in-the-middle" issue, they still fail to reliably identify relevant documents in LongSeal when faced with numerous distractors. To facilitate future work, we release SealQA at https://huggingface.co/datasets/vtllms/sealqa.

Applications · Everything Else

Yuhan Guo, cong guo, Aiwen Sun, Hongliang He, Xinyu Yang, Yue Lu, Yingji Zhang, Xuntao Guo, Dong Zhang, Jianzhuang Liu 等

Multimodal large-scale models have significantly advanced the development of web agents, enabling them to perceive and interact with the digital environment in a manner analogous to human cognition. In this paper, we argue that web agents must first acquire sufficient knowledge to engage in cognitive reasoning effectively. Therefore, we decompose a web agent's capabilities into two essential stages: knowledge content learning and cognitive processes. To formalize this, we propose Web-CogKnowledge Framework, which categorizes knowledge into Factual, Conceptual, and Procedural domains. In this framework, knowledge content learning corresponds to the agent's processes of Memorizing and Understanding, which rely on the former two types of knowledge, respectively, representing the "what" of learning. Conversely, cognitive processes correspond to Exploring, grounded in Procedural knowledge, defining the "how" of reasoning and action. To facilitate knowledge acquisition, we construct the Web-CogDataset, a structured resource curated from 14 real-world websites, designed to instill the core knowledge necessary for a web agent systematically. This dataset serves as the agent's conceptual grounding—the "nouns" upon which comprehension is built—as well as the basis for learning how to reason and act. Building on this foundation, we operationalize these processes through a novel knowledge-driven Chain-of-Thought (CoT) reasoning framework, developing and training our proposed multimodal web agent, the Web-CogReasoner. Extensive experimentation reveals its significant superiority over existing models, particularly in its capacity for generalization to unseen tasks where its structured knowledge proves decisive. To facilitate rigorous and systematic evaluation, we introduce the Web-CogBench, a comprehensive evaluation suite designed to assess and compare agent performance across the delineated knowledge domains and cognitive capabilities. Our code and data are open sourced at https://github.com/Gnonymous/Web-CogReasoner.

Reinforcement Learning · Deep RL

Xiyu Wei, Qingwei Zong, Xiaoguang Li, Eugene Yu, Sujian Li

Reinforcement Learning from Verifiable Rewards (RLVR) has significantly improved the performance of large language models (LLMs) on tasks with gold ground truth, such as code generation and mathematical reasoning. However, its application to open-ended question answering (QA) remains challenging, primarily due to the absence of reliable evaluation and verifiable reward signals. This difficulty is further compounded by the limitations of existing evaluation paradigms. Previous approaches typically rely on human feedback or LLM-as-judge strategies, which are costly, prone to reward hacking, and often fail to provide sufficiently discriminative or interpretable evaluation signals. To address these limitations, we introduce a schema for generating case-wise rubrics that are question-specific, content-based and stylistically sensitive, thereby evaluating both factual soundness and writing quality. Building on this schema, we propose QuRL (Open-Ended QA with Rubric-guided Reinforcement Learning), a framework that automatically mines rubrics for each question from easily accessible online sources and leverages them as reward signals. With these rubrics, QuRL employs the GRPO (Group Relative Policy Optimization) algorithm to guide the model in exploring the correct generation path. Extensive experiments show that our framework achieves significant improvements of total +17.0 points on evaluation benchmark, demonstrating the effectiveness of rubric-guided reinforcement learning for open-ended QA.

Ken Gu, Advait Bhat, Mike Merrill, Robert West, Xin Liu, Daniel McDuff, Tim Althoff

Evaluating the reasoning ability of language models (LMs) is complicated by their extensive parametric world knowledge, where benchmark performance often reflects factual recall rather than genuine reasoning. Existing datasets and approaches (e.g., temporal filtering, paraphrasing, adversarial substitution) cannot cleanly separate the two. We present SynthWorlds, a framework that disentangles task reasoning complexity from factual knowledge. In SynthWorlds, we construct parallel corpora representing two worlds with identical interconnected structure: a real-mapped world, where models may exploit parametric knowledge, and a synthetic-mapped world, where such knowledge is meaningless. On top of these corpora, we design two mirrored tasks as case studies: multi-hop question answering and page navigation, which maintain equal reasoning difficulty across worlds. Experiments in parametric-only (e.g., closed-book QA) and knowledge-augmented (e.g., retrieval-augmented) LM settings reveal a persistent *knowledge advantage gap*, defined as the performance boost models gain from memorized parametric world knowledge. Knowledge acquisition and integration mechanisms reduce but do not eliminate this gap, highlighting opportunities for system improvements. Fully automatic and scalable, SynthWorlds provides a controlled environment for evaluating LMs in ways that were previously challenging, enabling precise and testable comparisons of reasoning and memorization.

Theory · Interpretability and Visualization

Yavuz Faruk Bakman, Sungmin Kang, Zhiqi Huang, Duygu Nur Yaldiz, Catarina Belém, Chenyang Zhu, Anoop Kumar, Alfy Samuel, Daben Liu, Salman Avestimehr 等

Uncertainty Quantification (UQ) research has primarily focused on closed-book factual question answering (QA), while contextual QA remains unexplored, despite its importance in real-world applications. In this work, we focus on UQ for the contextual QA task and propose a theoretically grounded approach to quantify \emph{epistemic uncertainty}. We begin by introducing a task-agnostic, token-level uncertainty measure defined as the cross-entropy between the predictive distribution of the given model and the unknown true distribution. By decomposing this measure, we isolate the epistemic component and approximate the true distribution by a perfectly prompted, idealized model. We then derive an upper bound for epistemic uncertainty and show that it can be interpreted as semantic feature gaps in the given model’s hidden representations relative to the ideal model. We further apply this generic framework to the contextual QA task and hypothesize that three features approximate this gap: \emph{context-reliance} (using the provided context rather than parametric knowledge), \emph{context comprehension} (extracting relevant information from context), and \emph{honesty} (avoiding intentional lies). Using a top-down interpretability approach, we extract these features by using only a small number of labeled samples and ensemble them to form a robust uncertainty score. Experiments on multiple QA benchmarks in both in-distribution and out-of-distribution settings show that our method substantially outperforms state-of-the-art unsupervised (sampling-free and sampling-based) and supervised UQ methods, achieving up to a 13-point PRR improvement while incurring a negligible inference overhead. The code is available at https://github.com/Ybakman/Feature-Gaps.

Mert Vural, Alberto Bietti, Mahdi Soltanolkotabi, Denny Wu

Modern large language models (LLMs) excel at tasks that require storing and retrieving knowledge, such as factual recall and question answering. Transformers are central to this capability because they can encode information during training and retrieve it at inference. Existing theoretical analyses typically study transformers under idealized assumptions such as infinite data or orthogonal embeddings. In realistic settings, however, models are trained on finite datasets with non-orthogonal (random) embeddings. We address this gap by analyzing a single-layer transformer with random embeddings trained with (empirical) gradient descent on a simple token-retrieval task, where the model must identify an informative token within a length-$L$ sequence and learn a one-to-one mapping from tokens to labels. Our analysis tracks the ``early phase'' of gradient descent and yields explicit formulas for the model’s storage capacity---revealing a multiplicative dependence between sample size $N$, embedding dimension $d$, and sequence length $L$. We validate these scalings numerically and further complement them with a lower bound for the underlying statistical problem, demonstrating that this multiplicative scaling is intrinsic under non-orthogonal embeddings. Code to reproduce all experiments is publicly available.

Applications · Language, Speech and Dialog

David Bani-Harouni, Chantal Pellegrini, Paul Stangel, Ege Özsoy, Kamilia Zaripova, Nassir Navab, Matthias Keicher

A safe and trustworthy use of Large Language Models (LLMs) requires an accurate expression of confidence in their answers. We propose a novel Reinforcement Learning approach that allows to directly fine-tune LLMs to express calibrated confidence estimates alongside their answers to factual questions. Our method optimizes a reward based on the logarithmic scoring rule, explicitly penalizing both over- and under-confidence. This encourages the model to align its confidence estimates with the actual predictive accuracy. The optimal policy under our reward design would result in perfectly calibrated confidence expressions. Unlike prior approaches that decouple confidence estimation from response generation, our method integrates confidence calibration seamlessly into the generative process of the LLM. Empirically, we demonstrate that models trained with our approach exhibit substantially improved calibration and generalize to unseen tasks without further fine-tuning, suggesting the emergence of general confidence awareness. Our code is available at https://github.com/pasta99/RewardingDoubt.

Social Aspects · Accountability, Transparency and Interpretability

Piotr Komorowski, Elena Golimblevskaia, Reduan Achtibat, Thomas Wiegand, Sebastian Lapuschkin, Wojciech Samek

The capacity of Large Language Models (LLMs) to follow complex instructions and generate factually accurate text is critical for their real-world application. However, standard decoding methods often fail to robustly satisfy these requirements, while existing control techniques frequently degrade general output quality. In this work, we introduce Attribution-Guided Decoding (AGD), an interpretability-based decoding strategy. Instead of directly manipulating model activations, AGD considers a set of high-probability output token candidates and selects the one that exhibits the highest attribution to a user-defined Region of Interest (ROI). This ROI can be flexibly defined over different parts of the model's input or internal components, allowing AGD to steer generation towards various desirable behaviors. We demonstrate AGD's efficacy across three challenging domains. For instruction following, we show that AGD significantly boosts adherence (e.g., improving the overall success rate on Llama 3.1 from 66.0\% to 79.1\%). For knowledge-intensive tasks, we show that guiding generation towards usage of internal knowledge components or contextual sources can reduce hallucinations and improve factual accuracy in both closed-book and open-book settings. Furthermore, we propose an adaptive, entropy-based variant of AGD that mitigates quality degradation and reduces computational overhead by applying guidance only when the model is uncertain. Our work presents a versatile, more interpretable, and effective method for enhancing the reliability of modern LLMs.