Image de couverture de livre

Characterizing LLM Abstention Behavior in Science QA with Context Perturbations

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Wen, Bingbing, Howe, Bill, Wang, Lucy Lu
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Know Your Limits: A Survey of Abstention in Large Language Models
par: Wen, Bingbing, et autres
Publié: (2024)

STOP: Structured On-Policy Pruning of Long-Form Reasoning in Low-Data Regimes
par: Xu, Chenjun, et autres
Publié: (2026)

MixAtlas: Uncertainty-aware Data Mixture Optimization for Multimodal LLM Midtraining
par: Wen, Bingbing, et autres
Publié: (2026)

Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
par: Cao, Zongwan, et autres
Publié: (2026)

ML-EAT: A Multilevel Embedding Association Test for Interpretable and Transparent Social Science
par: Wolfe, Robert, et autres
Publié: (2024)

Epistemic Alignment: A Mediating Framework for User-LLM Knowledge Delivery
par: Clark, Nicholas, et autres
Publié: (2025)

Selective "Selective Prediction": Reducing Unnecessary Abstention in Vision-Language Reasoning
par: Srinivasan, Tejas, et autres
Publié: (2024)

Mitigating LLM Hallucinations via Conformal Abstention
par: Yadkori, Yasin Abbasi, et autres
Publié: (2024)

Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions
par: Atif, Farah, et autres
Publié: (2025)

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
par: Zong, Haotian, et autres
Publié: (2026)

Towards Zero-Shot Annotation of the Built Environment with Vision-Language Models (Vision Paper)
par: Han, Bin, et autres
Publié: (2024)

CQA-Eval: Designing Reliable Evaluations of Multi-paragraph Clinical QA under Resource Constraints
par: Bologna, Federica, et autres
Publié: (2025)

What External Knowledge is Preferred by LLMs? Characterizing and Exploring Chain of Evidence in Imperfect Context for Multi-Hop QA
par: Chang, Zhiyuan, et autres
Publié: (2024)

Can Large Language Models Integrate Spatial Data? Empirical Insights into Reasoning Strengths and Computational Weaknesses
par: Han, Bin, et autres
Publié: (2025)

NovelHopQA: Diagnosing Multi-Hop Reasoning Failures in Long Narrative Contexts
par: Gupta, Abhay, et autres
Publié: (2025)

When to Speak, When to Abstain: Contrastive Decoding with Abstention
par: Kim, Hyuhng Joon, et autres
Publié: (2024)

MASH: Modeling Abstention via Selective Help-Seeking
par: Gul, Mustafa Omer, et autres
Publié: (2025)

DetectiveQA: Evaluating Long-Context Reasoning on Detective Novels
par: Xu, Zhe, et autres
Publié: (2024)

Expect the Unexpected: FailSafe Long Context QA for Finance
par: Kamble, Kiran, et autres
Publié: (2025)

KG-MuLQA: A Framework for KG-based Multi-Level QA Extraction and Long-Context LLM Evaluation
par: Tatarinov, Nikita, et autres
Publié: (2025)

Representation Bias of Adolescents in AI: A Bilingual, Bicultural Study
par: Wolfe, Robert, et autres
Publié: (2024)

Knowledge Graph Guided Evaluation of Abstention Techniques
par: Vasisht, Kinshuk, et autres
Publié: (2024)

Geometry-Calibrated Conformal Abstention for Language Models
par: Xu, Rui, et autres
Publié: (2026)

Effective Skill Unlearning through Intervention and Abstention
par: Li, Yongce, et autres
Publié: (2025)

Dataset Scale and Societal Consistency Mediate Facial Impression Bias in Vision-Language AI
par: Wolfe, Robert, et autres
Publié: (2024)

QA-LIGN: Aligning LLMs through Constitutionally Decomposed QA
par: Dineen, Jacob, et autres
Publié: (2025)

InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification
par: Trienes, Jan, et autres
Publié: (2024)

According to Me: Long-Term Personalized Referential Memory QA
par: Mei, Jingbiao, et autres
Publié: (2026)

KnowGuard: Knowledge-Driven Abstention for Multi-Round Clinical Reasoning
par: Dang, Xilin, et autres
Publié: (2025)

GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence
par: Zhao, Yibo, et autres
Publié: (2026)

Augmenting LLM Reasoning with Dynamic Notes Writing for Complex QA
par: Maheshwary, Rishabh, et autres
Publié: (2025)

StorySparkQA: Expert-Annotated QA Pairs with Real-World Knowledge for Children's Story-Based Learning
par: Chen, Jiaju, et autres
Publié: (2023)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
par: Abdaljalil, Samir, et autres
Publié: (2026)

MKA: Leveraging Cross-Lingual Consensus for Model Abstention
par: Duwal, Sharad
Publié: (2025)

RepoQA: Evaluating Long Context Code Understanding
par: Liu, Jiawei, et autres
Publié: (2024)

Do LLM Self-Explanations Help Users Predict Model Behavior? Evaluating Counterfactual Simulatability with Pragmatic Perturbations
par: Hong, Pingjun, et autres
Publié: (2026)

TIAR: Trajectory-Informed Advantage Reweighting for LLM Abstention Learning
par: Pan, Muyu, et autres
Publié: (2026)

Shuffle the Context: RoPE-Perturbed Self-Distillation for Long-Context Adaptation
par: Li, Zichong, et autres
Publié: (2026)

Knowing When Not to Answer: Evaluating Abstention in Multimodal Reasoning Systems
par: Madhusudhan, Nishanth, et autres
Publié: (2026)

PaperHelper: Knowledge-Based LLM QA Paper Reading Assistant
par: Yin, Congrui, et autres
Publié: (2025)