论文检索

Mohammadsadegh Abolhasani, Reza Mousavi, Paul Jen-Hwa Hu

Analyses of parasocial cues in live-stream chats require accurate, efficient, and scalable annotation. However, manual annotation is tedious, and large language models (LLMs) often make mistakes when applying subjective, discourse-dependent labels. This study proposes Context-aware Batching for Stream Annotation with LLMs (CaBSALLM), an efficient pipeline that incorporates lightweight conversational context and a novel dynamic batching method to improve throughput and scalability. Compared with state-of-the-art pipelines, this generalizable approach is significantly more time- and cost-efficient while achieving comparable or better predictive performance and agreement.

Seyedali Mohammadi, Manas Gaur, Francis Ferraro

Scientific feasibility assessment asks whether a claim is consistent with established knowledge and whether experimental evidence could support or refute it. We frame feasibility assessment as a diagnostic reasoning task in which, given a hypothesis, a model predicts feasible or infeasible and justifies its decision. We evaluate large language models (LLMs) under controlled knowledge conditions (hypothesis-only, with experiments, with outcomes, or both) and probe robustness by progressively removing portions of the experimental and/or outcome context. Across multiple LLMs and two datasets, providing outcome evidence is generally more reliable than providing experiment descriptions. Outcomes tend to improve accuracy beyond what internal knowledge alone provides, whereas experimental text can be brittle and may degrade performance when the context is incomplete. These findings clarify when experimental evidence benefits LLM-based feasibility assessment and when it introduces fragility.

Lechen Zhang, Yunxiang Zhang, Wei Hu, Lu Wang

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the pursuit of data-efficient training methods. To address this, we propose a skill-centric distillation framework that efficiently transfers reasoning ability to weaker models with two components: (1) Skill-based data selection, which prioritizes examples targeting the student model’s weaker skills, and (2) Skill-aware fine-tuning, which encourages explicit skill decomposition during problem solving. With only 1,000 training examples selected from a 100K teacher-generated corpus, our method surpasses random SFT baselines by +1.6% on Qwen3-4B and +1.4% on Qwen3-8B across five mathematical reasoning benchmarks. Further analysis confirms that these gains concentrate on skills emphasized during training, highlighting the effectiveness of skill-centric training for efficient reasoning distillation.

Tanmay Parekh, Ella Hofmann-Coyle, Shuyi Wang, Sachith Sri Ram Kothur, Srivas Prasad, Yunmo Chen

LLM-based agents for text-to-SQL often struggle with latency-performance trade-off, where performance improvements come at the cost of latency or vice versa. We reformulate text-to-SQL generation within the lens of software test coverage where the original query is prepared with a suite of test cases with simpler, atomic SQLs that are executed in parallel and together ensure semantic coverage of the original query. After iterating on test case coverage, the final SQL is generated only when enough information is gathered, leveraging the explored test case SQLs to ground the final generation. We validated our framework on a state-of-the-art benchmark for text-to-SQL, Spider 2.0, achieving a new state-of-the-art with 70.2% execution accuracy.

Havva Alizadeh Noughabi, Fattane Zarrinkalam, Ali Dehghantanha

GraphRAG augments large language models with structured knowledge graphs, enabling graph-based context selection and a more integrated view of the knowledge space. However, recent work shows that GraphRAG exposes a new attack surface: corpus-level knowledge poisoning can inject spurious entities and relationships during graph construction, corrupting query-specific subgraphs and steering the generator toward incorrect answers. We propose Hop-wise Guard for GraphRAG (HoG-GRAG), a defense layer between retriever and generator that decomposes multi-hop questions into ordered subqueries, monitors hop-wise execution for poisoning-induced inconsistencies, and locally repairs the retrieved subgraph by pruning compromised entities and relationships and adding only minimal missing evidence. Experiments on multi-hop datasets and multiple GraphRAG configurations show that HoG-GRAG recovers a large fraction of the lost performance. The code is available at https://github.com/CyberScienceLab/HoG-GRAG.

Ayoub Hammal, Pierre Zweigenbaum, Caio Corro

Recent works proposed test-time alignment methods that rely on a small aligned model as a proxy that guides the generation of a larger base (unaligned) model. The implicit reward approach skews the large model distribution, whereas the nudging approach defers the generation of the next token to the small aligned model when the large base one is unconfident about its outcome. In this work, we first show that both approaches can be reduced to sampling from similar graphical models, where they differ only in the definition of a rejection criterion (or distribution). Moreover, we argue that the confidence criterion is ill-motivated due to linguistic phenomena like ambiguous phrasing. We propose a novel rejection criterion based on a conservative confidence bet. Experimentally, our novel approach outperforms previous work on several datasets.

Cheng Wang, Qin Liu, Wenxuan Zhou, Muhao Chen

Group Relative Policy Optimization (GRPO) has emerged as a promising approach for improving the reasoning capabilities of large language models. However, it struggles to effectively balance the trade-off between exploration and exploitation during training, often resulting in suboptimal performance. Motivated by the theoretical insight that changes in entropy are governed by the covariance between token probabilities and their corresponding advantages, we propose a hyperparameter-free, covariance-weighted optimization method that dynamically down-weights extreme token-level updates via a Gaussian kernel. This approach automatically reduces the instability caused by the exploration-exploitation trade-off while preserving informative learning signals. Extensive empirical evaluations show that our approach improves downstream performance across reasoning benchmarks compared with GRPO, and effectively stabilizes entropy as training progresses.

Zhenhan Huang

As human-agent interaction (HAI) evolves toward long-term social companionship, users expect *Original Character (OC)* agents to maintain a consistent persona, manage shared memories, and adapt to ever-changing preferences. However, LLM-based agents optimized by prompting or SFT exhibit a generalization gap: they behave as myopic instruction followers, leading to cascading errors in multi-turn interactions. For the agents to learn trajectory-level value functions that enable farsighted decision-making, we propose the NSARL framework, which formalizes OC companion agents’ interactions as a POMDP and decomposes the agent into three sub-policies (Router, Memory, and Persona), optimized via closed-loop RL from AI feedback (RLAIF) with verifiable rewards in a graph-constrained action space. Our preliminary experiments indicate a trade-off: SFT yields stronger persona generation, while NSARL improves structural logic, through conservative strategies (e.g., over-routing) that increase workflow completeness, advocating for a hybrid deployment strategy.

Xi Fang, Weijie Xu, Yuchong Zhang, Scott Nickleach, Stephanie Eckman, Chandan K. Reddy

When an AI assistant remembers that Sarah is a single mother working two jobs, does it interpret her stress differently than if she were a wealthy executive? As personalized AI systems increasingly incorporate long-term user memory, understanding how this memory shapes emotional reasoning is critical. We investigate how user memory affects emotional intelligence in large language models (LLMs) by evaluating 15 models on human validated emotional intelligence tests. We find that identical scenarios paired with different user profiles produce systematically divergent emotional interpretations. Across validated user-independent emotional scenarios and diverse user profiles, systematic biases emerged in several high-performing LLMs where advantaged profiles received more accurate emotional interpretations. Moreover, LLMs demonstrate significant disparities across demographic factors in emotion understanding and supportive recommendations tasks, indicating that personalization mechanisms can embed social hierarchies into models’ emotional reasoning. These results highlight a key challenge for memory-enhanced AI: systems designed for personalization may inadvertently reinforce social inequalities.

Venkata S Govindarajan, Laura Biester

Textual humor is enormously diverse and computational studies need to account for this range, including intentionally bad humor. In this paper, we curate and analyze a novel corpus of sentences from the Bulwer-Lytton Fiction Contest to better understand "bad" humor in English. Standard humor detection models perform poorly on our corpus, and an analysis of literary devices finds that these sentences combine features common in existing humor datasets (e.g., puns, irony) with metaphor, metafiction and simile. LLMs prompted to synthesize contest-style sentences imitate the form but exaggerate the effect by over-using certain literary devices, and including far more novel adjective-noun bigrams than human writers.

Imranul Ashrafi, Inigo Jauregi Unanue, Massimo Piccardi

Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on their internal representations. Recently, a prominent and effective approach, RE-Control (Kong et al., 2024), has proposed leveraging an external value function trained over the LLM’s hidden states to guide generation via gradient-based editing. While effective, this method overlooks a key characteristic of alignment tasks, i.e. that they are typically formulated as learning from human preferences between candidate responses. To address this, in this paper we propose a novel preference-based training framework, **Pref-CTRL**, that uses a multi-objective value function to better reflect the structure of preference data. Our approach has outperformed RE-Control on two benchmark datasets and showed greater generalization on out-of-domain datasets. Our source code is available at https://github.com/UTS-nlPUG/pref-ctrl.

Trapoom Ukarapol, Pakhapoom Sarapat, Nut Chukamphaeng

Large language models (LLMs) sometimes exhibit language confusion when generating non-English text. Existing approaches typically rely on fine-tuning to mitigate this issue. In contrast, we propose a tuning-free paradigm for reducing language confusion. Within this paradigm, we introduce two methods: Language-Aware Token Boosting (LATB), which applies targeted perturbations to tokens associated with the desired language, and Adaptive Language-Aware Token Boosting (Adaptive-LATB), which dynamically adjusts these perturbations based on the model’s confidence in the intended language. Experiments demonstrate that our methods effectively improve multilingual alignment by reducing language confusion, while maintain the summarization quality without requiring any additional fine-tuning. Our code is publicly available.[<https://github.com/scbdatax/genai-datax-language-aware-token-boosting>].

Andreas van Cranenburgh, Xiaoyan Yang, Alvanita, Cecilia Nicole Di Domenico, Maria Ferragud, Arianna Graciotti, Andreea Gabriela Ion, Byungjun Kim, Seonyeong Park, Noa Visser Solissa 等

We present a multilingual coreference dataset of 827k tokens of fiction in 7 languages: Bahasa Indonesia, Chinese, Dutch, English, Italian, Korean, and Spanish. The dataset includes full stories of diverse lengths, ranging from 500 to 17k words. We discuss our annotation scheme focusing on characters and language-specific challenges we encountered. Finally we present evaluation results of a neural coreference system trained on our dataset. We show that jointly training a system across all languages provides a strong improvement over monolingually trained models. The dataset is available under a creative commons license in CoNLL-2012 and CorefUD format at https://github.com/GOLEM-lab/GOLEMcoref/

Yong Guan, Zhiyuan Li, Shaoru Guo

Events exhibit rich semantic relations that are essential for understanding the unfolding of real-world processes. Although large language models (LLMs) have achieved strong performance on event relation extraction, how event relations are internally represented and utilized remains unclear. In this paper, we present UERLens, an interpretability framework for understanding event relations in LLMs. Specifically, we first construct UERBench, a counterfactual dataset for event relation analysis that covers causal, temporal, and sub-event relations. Based on counterfactual pairs, we identify relation-sensitive internal features by comparing model activations. We then examine the functional role of these features through model manipulation, including model intervention and model training. Experimental results show that event relations are encoded through structured and layer-specific internal features. Disabling relation-sensitive features leads to performance drops of over 22%, while enhancing them yields improvements of up to 7%. Furthermore, leveraging these interpretable features to train a lightweight classifier significantly improves event relation extraction, achieving F1 gains of up to 24% for causal relations.

Yunxiang MO, Tianshi Zheng, Qing Zong, Jiayu Liu, Baixuan Xu, Yauwai Yim, Chunkit Chan, Jiaxin Bai, Yangqiu Song

Multimodal abductive reasoning — the generation and selection of explanatory hypotheses from partial observations — is a cornerstone of intelligence. Current evaluations of such ability in vision–language models (VLMs) are largely confined to static, single-agent tasks. Inspired by Dixit, we introduce DixitWorld, a comprehensive evaluation suite designed to deconstruct this challenge. DixitWorld features two core components: DixitArena, a dynamic, multi-agent environment that evaluates both hypothesis generation (a "storyteller" crafting cryptic clues) and hypothesis selection ("listeners" choosing the target image from decoys) under imperfect information; and DixitBench, a static QA benchmark that isolates the listener’s task for efficient, controlled evaluation. Results from DixitArena reveal distinct, role-dependent behaviors: smaller open-source models often excel as creative storytellers, producing imaginative yet less discriminative clues, whereas larger proprietary models demonstrate superior overall performance, particularly as listeners. Performance on DixitBench strongly correlates with listener results in DixitArena, validating it as a reliable proxy for hypothesis selection. Our findings reveal a key trade-off between generative creativity and discriminative understanding in multimodal abductive reasoning, a central challenge for developing more balanced and capable vision-language agents.

Alberto Testoni, Iacer Calixto

Safe clinical deployment of Large Language Models (LLMs) requires not only high accuracy but also robust uncertainty calibration to ensure models defer to clinicians when appropriate. Our paper investigates how social descriptors of a patient (specifically sexual orientation and religious affiliation) distort these uncertainty signals and model accuracy. Evaluating nine general-purpose and biomedical LLMs on 2,364 medical questions and their counterfactual variants, we demonstrate that identity markers cause a "calibration crisis". *Homosexual* markers consistently trigger performance drops, and intersectional identities produce idiosyncratic, non-additive harms to calibration. Moreover, a clinician-validated case study in an open-ended generation setting confirms that these failures are not an artifact of the multiple-choice format. Our results demonstrate that the presence of social identity cues does not merely shift predictions; it affects the reliability of confidence signals, posing a significant risk to equitable care and safe deployment in confidence-based clinical workflows.

Chaewon Yoon, Dongjun Kim, Hyun-Je Song

Large language models (LLMs) trained on massive text corpora may inadvertently memorize sensitive or copyrighted content, motivating the need for more targeted unlearning. Selective LLM unlearning focuses on identifying token-level or span-level unlearning targets within a text, rather than treating entire sequences as unlearning targets. However, many existing selective approaches depend on external supervision to identify unlearning targets, which may misalign unlearning objectives with the model’s internal behavior. In this paper, we propose a selective span-level unlearning method that is grounded entirely in model-intrinsic information. Our method first estimates token-level importance scores by contrasting gradient information induced by forget and retain datasets, identifying tokens that disproportionately contribute to information targeted for unlearning. These token-level importance scores are then used as anchors to identify coherent span-level unlearning targets via a self-consistency–based generation process, allowing the model to determine stable spans based on its own predictions. Experiments on two LLM unlearning benchmarks show that our approach achieves comparable unlearning performance while substantially better preserving retained knowledge.

Rhea Kapur, Robert D. Hawkins, Elisa Kreiss

Vision-language models (VLMs) are increasingly used to make visual content accessible via text-based descriptions. In current systems, however, description specificity is often conflated with their length. We argue that these two concepts must be disentangled: descriptions can be concise yet dense with information, or lengthy yet vacuous. We define specificity relative to a contrast set, where a description is more specific to the extent that it picks out the target image better than other possible images. We construct a dataset that controls for length while varying information content, and validate that people reliably prefer more specific descriptions regardless of length. We find that controlling for length alone cannot account for differences in specificity; it matters how the length budget is applied. These results support evaluation approaches that directly prioritize specificity over verbosity.

Kisu Yang, Yoonna Jang, Hwanseok Jang, Kenneth Choi, Isabelle Augenstein, Heuiseok Lim

Lowering the numerical precision of model parameters and computations is widely adopted to improve the efficiency of retrieval systems. However, when computing relevance scores between the query and documents in low-precision, we observe spurious ties due to the reduced granularity. This introduces high variability in the results based on tie resolution, making the evaluation less reliable. To address this, we propose a more robust retrieval evaluation protocol designed to reduce score variation. It consists of: (1) High-Precision Scoring (HPS), which upcasts the final scoring step to higher precision to resolve tied candidates with minimal computational cost; and (2) Tie-aware Retrieval Metrics (TRM), which report expected scores, range, and bias to quantify order uncertainty of tied candidates. Our experiments test multiple models with three scoring functions on twelve retrieval datasets to demonstrate that HPS dramatically reduces tie-induced instability, and TRM accurately recovers expected metric values. This combination enables a more consistent and reliable evaluation system for lower-precision retrieval.

Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, Sattvik Sahai, Prasoon Goyal, Kai-Wei Chang, Tao Zhang, Rahul Gupta

Recent work has shown that fine-tuning on insecure code data can trigger an emergent misalignment (EMA) phenomenon, where models generate malicious responses even to prompts unrelated to the original insecure code-writing task. Such cross-domain generalization of harmful behavior underscores the need for a deeper understanding of the algorithms, tasks, and datasets that induce emergent misalignment. In this work, we extend this study by demonstrating that emergent misalignment can also arise from narrow refusal unlearning in specific domains. We perform refusal unlearning on Cybersecurity and Safety concept, and evaluate EMA by monitoring refusal scores across seven responsible AI (RAI) domains, Cybersecurity, Safety, Toxicity, Bias, Sensitive Content, Medical/Legal, and Privacy. Our work shows that narrow domain unlearning can yield compliance responses for the targeted concept, however, it may also propagate EMA to unrelated domains. Among the two intervened concepts, Cybersecurity and Safety, we find that the safety concept can have larger EMA impact, i.e, causing lower refusal scores, across other unrelated domains such as bias. We observe this effect consistently across two model families, Mistral-7b-0.3v, and Qwen-7b-2.5. Further, we show that refusal unlearning augmented with cross-entropy loss function on a small set of retain data from the affected domains can largely, if not fully, restore alignment across the impacted domains while having lower refusal rate on the concept we perform unlearning on. To investigate the underlying causes of EMA, we analyze concept entanglements at the representation level via concept vectors. Our analysis reveals that concepts with higher representation similarity in earlier layers are more susceptible to EMA after intervention when the refusal stream is altered through targeted refusal unlearning.