论文检索

Kang He, Kaushik Roy

Large language models (LLMs) have achieved remarkable multi-step reasoning capabilities across various domains. However, LLMs still face distinct challenges in complex logical reasoning, as (1) proof-finding requires systematic exploration and the maintenance of logical coherence and (2) searching the right combination of premises at each reasoning step is inherently challenging in tasks with large premise space. To address this, we propose LogicTree, an inference-time modular framework employing algorithm-guided search to automate structured proof exploration and ensure logical coherence. Advancing beyond tree-of-thought (ToT), we incorporate caching mechanism into LogicTree to enable effective utilization of historical knowledge, preventing reasoning stagnation and minimizing redundancy. Furthermore, we address the combinatorial complexity of premise search by decomposing it into a linear process. The refined premise selection restricts subsequent inference to at most one derivation per step, enhancing reasoning granularity and enforcing strict step-by-step reasoning. Additionally, we introduce two LLM-free heuristics for premise prioritization, enabling strategic proof search. Experimental results on five datasets demonstrate that LogicTree optimally scales inference-time computation to achieve higher proof accuracy, surpassing chain-of-thought (CoT) and ToT with average gains of 23.6% and 12.5%, respectively, on GPT-4o. Moreover, within LogicTree, GPT-4o outperforms o3-mini by 7.6% on average.

Younghun Lee, Dan Goldwasser

Large Language Models (LLMs) not only have solved complex reasoning problems but also exhibit remarkable performance in tasks that require subjective decision-making. Existing studies suggest that LLM generations can convey subjectivity to some extent, yet exploring whether LLMs can account for individual-level subjectivity has not been sufficiently studied. In this paper, we characterize the subjectivity of individuals on social media and infer their moral judgments using LLMs. We propose a framework, SolAr (Subjective Ground with Value Abstraction), that observes value conflicts and trade-offs in the user-generated texts to better represent subjective ground of individuals. Empirical results demonstrate that our framework enhances overall inference performance, with notable improvements for users with limited data and in controversial situations. Additionally, we qualitatively show that SolAr provides explanations about individuals’ value preferences, which can further account for their judgments.

Yuanchang Luo, Daimeng Wei, Shaojun Li, Hengchao Shang, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Xiaoyu Chen, Zhiqiang Rao, Jinlong Yang 等

End-to-end automatic speech recognition systems often fail to transcribe domain-speciffcnamed entities, causing catastrophic failuresin downstream tasks. Numerous fast and lightweight named entity correction (NEC) models have been proposed in recent years. These models, mainly leveraging phonetic-level edit distance algorithms, have shown impressive performances. However, when theforms of the wrongly-transcribed words(s) and the ground-truth entity are signiffcantly different, these methods often fail to locate the wrongly transcribed words in hypothesis, thus limiting their usage. We propose a novel NEC method that utilizes speech sound features to retrieve candidate entities. With speech sound features and candidate entities, we inovatively design a generative method to annotate entityerrors in ASR transcripts and replace the textwith correct entities. This method is effective inscenarios of word form difference. We test ourmethod using open-source and self-constructed test sets. The results demonstrate that our NEC method can bring signiffcant improvement to entity accuracy. We will open source our self constructed test set and training data.

Hyeonseok Moon, Seongtae Hong, Jaehyung Seo, Heuiseok Lim

Recent frontier-level LLMs have saturated many previously difficult benchmarks, leaving little room for further differentiation. This progress highlights the need for challenging benchmarks that provide objective verification. In this paper, we introduce MCBench, a benchmark designed to evaluate whether LLMs can execute string-matching NLP metrics by strictly following step-by-step instructions. Unlike prior benchmarks that depend on subjective judgments or general reasoning, MCBench offers an objective, deterministic and code-verifiable evaluation. This setup allows us to systematically test whether LLMs can maintain accurate step-by-step execution, including instruction adherence, numerical computation, and long-range consistency in handling intermediate results. To ensure objective evaluation of these abilities, we provide a parallel reference code that can evaluate the accuracy of LLM output. We provide three evaluative metrics and three benchmark variants designed to measure the detailed instruction understanding capability of LLMs. Our analyses show that MCBench serves as an effective and objective tool for evaluating the capabilities of cutting-edge LLMs

YiQiu Guo, Yuchen Yang, Zhe Chen, Pingjie Wang, Yusheng Liao, Ya Zhang, Yanfeng Wang, Yu Wang

The reliability of large language models remains a critical challenge, particularly due to their susceptibility to hallucinations and factual inaccuracies during text generation. Existing solutions either underutilize models’ self-correction with preemptive strategies or use costly post-hoc verification. To further explore the potential of real-time self-verification and correction, we present Dynamic Self-Verify Decoding (DSVD), a novel decoding framework that enhances generation reliability through real-time hallucination detection and efficient error correction. DSVD integrates two key components: (1) parallel self-verification architecture for continuous quality assessment, (2) dynamic rollback mechanism for targeted error recovery. Extensive experiments across five benchmarks demonstrate DSVD’s effectiveness, achieving significant improvement in truthfulness (Quesetion-Answering) and factual accuracy (FActScore). Results show the DSVD can be further incorporated with existing faithful decoding methods to achieve stronger performance. Our work establishes that real-time self-verification during generation offers a viable path toward more trustworthy language models without sacrificing practical deployability.

Xin Gao, Ruiyi Zhang, Daniel Du, Saurabh Mahindre, Sai Ashish Somayajula, Pengtao Xie

Large Language Models (LLMs) are widely used for temporal prediction, but their reliance on pretraining data raises contamination concerns, as accurate predictions on pre-cutoff test data may reflect memorization rather than reasoning, leading to an overestimation of their generalization capability. With the recent emergence of prompting-based unlearning techniques, a natural question arises: Can LLMs be prompted to simulate an earlier knowledge cutoff? In this work, we investigate the capability of prompting to simulate earlier knowledge cutoff in LLMs. We construct three evaluation datasets to assess the extent to which LLMs can forget (1) direct factual knowledge, (2) semantic shifts, and (3) causally related knowledge. Results demonstrate that while prompt-based simulated knowledge cutoffs show effectiveness when directly queried with the information after that date, they struggle to induce forgetting when the forgotten content is not directly asked but causally related to the query. These findings highlight the need for more rigorous evaluation settings when applying LLMs for temporal prediction tasks. The full dataset and evaluation code are available at https://github.com/gxx27/time_unlearn.

Hong Zhang, Feng Zhao, Ruilin Zhao, Cheng Yan, Kangzheng Liu

Large Language Models (LLMs) have demonstrated a remarkable understanding of language nuances through instruction tuning, enabling them to effectively tackle various natural language processing tasks. Recent research has focused on the quality of instruction data rather than the quantity of instructions. However, existing high-quality instruction selection methods rely on external models or rules, overlooking the intrinsic association between pre-trained model and instruction data, making it difficult to select data that align with the preferences of pre-trained model. To address this challenge, we propose a strategy that utilizes noise injection to identify the quality of instruction data, without relying on external model. We also implement the strategy of combining inter-class diversity and intra-class diversity to improve model performance. The experimental results demonstrate that our method significantly outperforms the model trained on the entire dataset and established baselines. Our study provides a new perspective on noise injection in the field of instruction tuning, and also illustrates that the pre-trained model itself should be considered in defining high-quality. Additionally, we publish our selected high-quality instruction data.

Boxiang Ma, Ru Li, Wang Yuanlong, Hongye Tan, Xiaoli Li

Driven by vast and diverse textual data, large language models (LLMs) have demonstrated impressive performance across numerous natural language processing (NLP) tasks. Yet, a critical question persists: does their generalization arise from mere memorization of training data or from deep semantic understanding? To investigate this, we propose a bi-perspective evaluation framework to assess LLMs’ scenario cognition—the ability to link semantic scenario elements with their arguments in context. Specifically, we introduce a novel scenario-based dataset comprising diverse textual descriptions of fictional facts, annotated with scenario elements. LLMs are evaluated through their capacity to answer scenario-related questions (model output perspective) and via probing their internal representations for encoded scenario elements-argument associations (internal representation perspective). Our experiments reveal that current LLMs predominantly rely on superficial memorization, failing to achieve robust semantic scenario cognition, even in simple cases. These findings expose critical limitations in LLMs’ semantic understanding and offer cognitive insights for advancing their capabilities.

Han Liu, Ruoyao Wen, Srijith Nair, Jia Liu, Wenjing Lou, Chongjie Zhang, William Yeoh, Yevgeniy Vorobeychik, Ning Zhang

To address data locality and privacy restrictions, Federated Learning (FL) has recently been adopted to fine-tune large language models (LLMs), enabling improved performance on various downstream tasks without requiring aggregated data. However, the repeated exchange of model updates in FL can result in prohibitively high communication costs, hindering the distributed learning process. To address this challenge, we propose EcoLoRA, a novel communication-efficient federated fine-tuning framework for LLMs. Leveraging the modular structure, we propose a round-robin segment sharing scheme, where each client uploads only a complementary LoRA segment per round to reduce network bandwidth. It is further combined with adaptive sparsification methods tailored to LoRA’s training dynamics and lossless encoding techniques. We conduct extensive evaluations on both question-answering and value-alignment tasks across multiple datasets and models. The results show that EcoLoRA significantly reduces communication overhead without compromising performance. For instance, it reduces communication time by up to 79% and total training time by up to 65%.

Tianshi Zheng, Cheng Jiayang, Chunyang Li, Haochen Shi, Zihao Wang, Jiaxin Bai, Yangqiu Song, Ginny Wong, Simon See

Modern large language models (LLMs) employ diverse logical inference mechanisms for reasoning, making the strategic optimization of these approaches critical for advancing their capabilities. This paper systematically investigate the **comparative dynamics** of inductive (System 1) versus abductive/deductive (System 2) inference in LLMs. We utilize a controlled analogical reasoning environment, varying modality (textual, visual, symbolic), difficulty, and task format (MCQ / free-text). Our analysis reveals System 2 pipelines generally excel, particularly in visual/symbolic modalities and harder tasks, while System 1 is competitive for textual and easier problems. Crucially, task format significantly influences their relative advantage, with System 1 sometimes outperforming System 2 in free-text rule-execution. These core findings generalize to broader in-context learning. Furthermore, we demonstrate that advanced System 2 strategies like hypothesis selection and iterative refinement can substantially scale LLM reasoning. This study offers foundational insights and actionable guidelines for strategically deploying logical inference to enhance LLM reasoning.

Anton Lavrouk, Tarek Naous, Alan Ritter, Wei Xu

The culture of the Post-Soviet states is complex, shaped by a turbulent history that continues to influence current events. In this study, we investigate the Post-Soviet cultural food knowledge of foundation models by constructing BORSch, a multi-modal dataset encompassing 1147 and 823 dishes in the Russian and Ukrainian languages, centered around the Post-Soviet region. We demonstrate that leading models struggle to correctly identify the origins of dishes from Post-Soviet nations in both text-only and multi-modal Question Answering (QA), instead over-predicting countries linked to the language the question is asked in. Through analysis of pre-training data, we show that these results can be explained by misleading dish-origin co-occurrences, along with linguistic phenomena such as Russian-Ukrainian code mixing. Finally, to move beyond QA-based assessments, we test models’ abilities to produce accurate visual descriptions of dishes. The weak correlation between this task and QA suggests that QA alone may be insufficient as an evaluation of cultural understanding.

Shubham Gandhi, Atharva Naik, Yiqing Xie, Carolyn Rose

We study cost-efficient collaboration between strong and weak language models for repository-level code generation, where the weak model handles simpler tasks at lower cost, and the most challenging tasks are delegated to the strong model. While many works propose architectures for this task, few analyze performance relative to cost. We evaluate a broad spectrum of collaboration strategies: context-based, pipeline-based, and dynamic, on GitHub issue resolution. Our most effective collaborative strategy achieves equivalent performance to the strong model while reducing the cost by 40%. Based on our findings, we offer actionable guidelines for choosing collaboration strategies under varying budget and performance constraints. Our results show that strong–weak collaboration substantially boosts the weak model’s performance at a fraction of the cost, pipeline and context-based methods being most efficient.

Mihir Parmar, Xin Liu, Palash Goyal, Yanfei Chen, Long Le, Swaroop Mishra, Hossein Mobahi, Jindong Gu, Zifeng Wang, Hootan Nakhost 等

Recent agent frameworks and inference-time algorithms often struggle with natural planning problems due to limitations in verifying generated plans or reasoning and varying complexity of instances within a single task. Many existing methods for these tasks either perform task-level verification without considering constraints or apply inference-time algorithms without adapting to instance-level complexity. To address these limitations, we propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents. Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms–Best of \mathcal{N}, Tree-of-Thought, and REBASE. In PlanGEN framework, the selection agent optimizes algorithm choice based on instance complexity, ensuring better adaptability to complex planning problems. Experimental results demonstrate significant improvements over the strongest baseline across multiple benchmarks, achieving state-of-the-art results on NATURAL PLAN (~8%\uparrow), OlympiadBench (~4%\uparrow), DocFinQA (~7%\uparrow), and GPQA (~1%\uparrow). Our key finding highlights that constraint-guided iterative verification improves inference-time algorithms, and adaptive selection further boosts performance on complex planning and reasoning problems.

Tingyu Song, Yilun Zhao, Siyue Zhang, Chen Zhao, Arman Cohan

Existing approaches typically rely on large-scale fine-tuning to adapt LLMs for information reranking tasks, which is computationally expensive. In this work, we demonstrate that modern LLMs can be effectively adapted using only minimal, high-quality supervision. To enable this, we design LIMRANK-SYNTHESIZER, a reusable and open-source pipeline for generating diverse, challenging, and realistic reranking examples. Using this synthetic data, we fine-tune our reranker model, LIMRANK. We evaluate LIMRANK on two challenging benchmarks, i.e., BRIGHT for reasoning-intensive retrieval and FollowIR for instruction-following retrieval. Our experiments demonstrate that LIMRANK achieves competitive performance, while being trained on less than 5% of the data typically used in prior work. Further ablation studies demonstrate the effectiveness of LIMRANK-SYNTHESIZER and the strong generalization capabilities of LIMRANK across downstream tasks, including scientific literature search and retrieval-augmented generation for knowledge-intensive problem solving.

Zheyuan Yang, Lyuhao Chen, Arman Cohan, Yilun Zhao

In this work, we present the first study to explore inference-time scaling on table reasoning tasks. We develop and evaluate two post-training strategies to enable inference-time scaling: distillation from frontier model reasoning traces and reinforcement learning with verifiable rewards (RLVR). For distillation, we introduce a large-scale dataset of reasoning traces generated by DeepSeek-R1, which we use to fine-tune LLMs into the Table-R1-SFT model. For RLVR, we propose task-specific verifiable reward functions and apply the GRPO algorithm to obtain the Table-R1-Zero model. We evaluate our Table-R1-series models across diverse table reasoning tasks, including short-form QA, fact verification, and free-form QA. Notably, the Table-R1-Zero model matches or exceeds the performance of GPT-4.1 and DeepSeek-R1, while using only a 7B-parameter LLM. It also demonstrates strong generalization to out-of-domain datasets. Extensive ablation and qualitative analyses reveal the benefits of instruction tuning, model architecture choices, and cross-task generalization, as well as emergence of essential table reasoning skills during RL training.

Tanmay Parekh, Yuxuan Dong, Lucas Bandarkar, Artin Kim, I-Hung Hsu, Kai-Wei Chang, Nanyun Peng

Event Detection (ED) – the task of identifying event mentions from natural language text – is critical for enabling reasoning in highly specialized domains such as biomedicine, law, and epidemiology. Data generation has proven to be effective in broadening its utility to wider applications without requiring expensive expert annotations. However, when existing generation approaches are applied to specialized domains, they struggle with label noise, where annotations are incorrect, and domain drift, characterized by a distributional mismatch between generated sentences and the target domain. To address these issues, we introduce SNaRe, a domain-aware synthetic data generation framework composed of three components: Scout, Narrator, and Refiner. Scout extracts triggers from unlabeled target domain data and curates a high-quality domain-specific trigger list using corpus-level statistics to mitigate domain drift. Narrator, conditioned on these triggers, generates high-quality domain-aligned sentences, and Refiner identifies additional event mentions, ensuring high annotation quality. Experimentation on three diverse domain ED datasets reveals how SNaRe outperforms the best baseline, achieving average F1 gains of 3-7% in the zero-shot/few-shot settings and 4-20% F1 improvement for multilingual generation. Analyzing the generated trigger hit rate and human evaluation substantiates SNaRe’s stronger annotation quality and reduced domain drift.

Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi, Kai-Wei Chang, Nanyun Peng

Zero-shot Event Detection (ED), the task of identifying event mentions in natural language text without any training data, is critical for document understanding in specialized domains. Understanding the complex event ontology, extracting domain-specific triggers from the passage, and structuring them appropriately overloads and limits the utility of Large Language Models (LLMs) for zero-shot ED. To this end, we propose DiCoRe, a divergent-convergent reasoning framework that decouples the task of ED using Dreamer and Grounder. Dreamer encourages divergent reasoning through open-ended event discovery, which helps to boost event coverage. Conversely, Grounder introduces convergent reasoning to align the free-form predictions with the task-specific instructions using finite-state machine guided constrained decoding. Additionally, an LLM-Judge verifies the final outputs to ensure high precision. Through extensive experiments on six datasets across five domains and nine LLMs, we demonstrate how DiCoRe consistently outperforms prior zero-shot, transfer-learning, and reasoning baselines, achieving 4–7% average F1 gains over the best baseline – establishing DiCoRe as a strong zero-shot ED framework.

Joohyung Yun, Doyup Lee, Wook-Shin Han

Multimodal document retrieval aims to retrieve query-relevant components from documents composed of textual, tabular, and visual elements. An effective multimodal retriever needs to handle two main challenges: (1) mitigate the effect of irrelevant contents caused by fixed, single-granular retrieval units, and (2) support multihop reasoning by effectively capturing semantic relationships among components within and across documents. To address these challenges, we propose LILaC, a multimodal retrieval framework featuring two core innovations. First, we introduce a layered component graph, explicitly representing multimodal information at two layers—each representing coarse and fine granularity—facilitating efficient yet precise reasoning. Second, we develop a late-interaction-based subgraph retrieval method, an edge-based approach that initially identifies coarse-grained nodes for efficient candidate generation, then performs fine-grained reasoning via late interaction. Extensive experiments demonstrate that LILaC achieves state-of-the-art retrieval performance on all five benchmarks, notably without additional fine-tuning. We make the artifacts publicly available at github.com/joohyung00/lilac.

Wafa Aissa, Thibault Bañeras-Roux, Elodie Vanzeveren, Lingyun Gao, Rodrigo Wilkens, Thomas François

This study presents a novel approach to assessing French text readability for adults with low literacy skills, addressing both global (full-text) and local (segment-level) difficulty. We introduce a dataset of 461 texts annotated using a difficulty scale developed specifically for this population. Using this corpus, we conducted a systematic comparison of key readability modeling approaches, including machine learning techniques based on linguistic variables, fine-tuning of CamemBERT, a hybrid approach combining CamemBERT with linguistic variables, and the use of generative language models (LLMs) to carry out readability assessment at both global and local levels.

Vatsal Malaviya, Agneet Chatterjee, Maitreya Patel, Yezhou Yang, Chitta Baral

Text-to-Image (T2I) models have recently achieved remarkable success in generating images from textual descriptions. However, challenges still persist in accurately rendering complex scenes where actions and interactions form the primary semantic focus. Our key observation in this work is that T2I models frequently struggle to capture nuanced and often implicit attributes inherent in action depiction, leading to generating images that lack key contextual details. To enable systematic evaluation, we introduce AcT2I, a benchmark designed to evaluate the performance of T2I models in generating images from action-centric prompts. We experimentally validate that leading T2I models do not fare well on AcT2I. We further hypothesize that this shortcoming arises from the incomplete representation of the inherent attributes and contextual dependencies in the training corpora of existing T2I models. We build upon this by developing a training-free, knowledge distillation technique utilizing Large Language Models to address this limitation. Specifically, we enhance prompts by incorporating dense information across three dimensions, observing that injecting prompts with temporal details significantly improves image generation accuracy, with our best model achieving an increase of 72%. Our findings highlight the limitations of current T2I methods in generating images that require complex reasoning and demonstrate that integrating linguistic knowledge in a systematic way can notably advance the generation of nuanced and contextually accurate images. Project Page : https://vatsal-malaviya.github.io/AcT2I/