Copertina

Answering the Unanswerable Is to Err Knowingly: Analyzing and Mitigating Abstention Failures in Large Reasoning Models

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Yi, Liu, Xiangyu, Sun, Zequn, Hu, Wei
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning
di: Zhu, Rongzhi, et al.
Pubblicazione: (2025)

Knowing When Not to Answer: Abstention-Aware Scientific Reasoning
di: Abdaljalil, Samir, et al.
Pubblicazione: (2026)

A Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
di: Cui, Yuanning, et al.
Pubblicazione: (2024)

Finetuning Generative Large Language Models with Discrimination Instructions for Knowledge Graph Completion
di: Liu, Yang, et al.
Pubblicazione: (2024)

Avoiding Knowledge Edit Skipping in Multi-hop Question Answering with Guided Decomposition
di: Liu, Yi, et al.
Pubblicazione: (2025)

CausalAbstain: Enhancing Multilingual LLMs with Causal Reasoning for Trustworthy Abstention
di: Sun, Yuxi, et al.
Pubblicazione: (2025)

Mitigating Lost-in-Retrieval Problems in Retrieval Augmented Multi-Hop Question Answering
di: Zhu, Rongzhi, et al.
Pubblicazione: (2025)

Mitigating LLM Hallucinations via Conformal Abstention
di: Yadkori, Yasin Abbasi, et al.
Pubblicazione: (2024)

AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
di: Kirichenko, Polina, et al.
Pubblicazione: (2025)

Beyond Static Summarization: Proactive Memory Extraction for LLM Agents
di: Yang, Chengyuan, et al.
Pubblicazione: (2026)

EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and Reasoning
di: Wei, Mingyang, et al.
Pubblicazione: (2026)

Dissecting Failure Dynamics in Large Language Model Reasoning
di: Zhu, Wei, et al.
Pubblicazione: (2026)

I-CALM: Incentivizing Confidence-Aware Abstention for LLM Hallucination Mitigation
di: Zong, Haotian, et al.
Pubblicazione: (2026)

Whispers that Shake Foundations: Analyzing and Mitigating False Premise Hallucinations in Large Language Models
di: Yuan, Hongbang, et al.
Pubblicazione: (2024)

Stop Before You Fail: Operational Capability Boundaries for Mitigating Unproductive Reasoning in Large Reasoning Models
di: Zhang, Qingjie, et al.
Pubblicazione: (2025)

Know More, Know Clearer: A Meta-Cognitive Framework for Knowledge Augmentation in Large Language Models
di: Chen, Hao, et al.
Pubblicazione: (2026)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
di: Mei, Zhiting, et al.
Pubblicazione: (2025)

Multi-Aspect Controllable Text Generation with Disentangled Counterfactual Augmentation
di: Liu, Yi, et al.
Pubblicazione: (2024)

Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
di: Guan, Weixin, et al.
Pubblicazione: (2026)

Energy Landscapes Enable Reliable Abstention in Retrieval-Augmented Large Language Models for Healthcare
di: Shankar, Ravi, et al.
Pubblicazione: (2025)

Hallucinate Less by Thinking More: Aspect-Based Causal Abstention for Large Language Models
di: Nguyen, Vy, et al.
Pubblicazione: (2025)

PRACTIQ: A Practical Conversational Text-to-SQL dataset with Ambiguous and Unanswerable Queries
di: Dong, Mingwen, et al.
Pubblicazione: (2024)

FiDeLiS: Faithful Reasoning in Large Language Model for Knowledge Graph Question Answering
di: Sui, Yuan, et al.
Pubblicazione: (2024)

Multilingual Medical Reasoning for Question Answering with Large Language Models
di: Ferrazzi, Pietro, et al.
Pubblicazione: (2025)

Can Language Models Analyze Data? Evaluating Large Language Models for Question Answering over Datasets
di: Xenofontos, Andreas, et al.
Pubblicazione: (2026)

ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agents
di: Zhang, Xiaohui, et al.
Pubblicazione: (2026)

Knowledge Graph Error Detection with Contrastive Confidence Adaption
di: Liu, Xiangyu, et al.
Pubblicazione: (2023)

Agentic Retrieval-Augmented Generation for Financial Document Question Answering
di: Shu, Yang, et al.
Pubblicazione: (2026)

I Could've Asked That: Reformulating Unanswerable Questions
di: Zhao, Wenting, et al.
Pubblicazione: (2024)

Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL
di: Yang, Yongjin, et al.
Pubblicazione: (2024)

Mitigating Hallucinations in Large Language Models via Causal Reasoning
di: Li, Yuangang, et al.
Pubblicazione: (2025)

Analyzing Nobel Prize Literature with Large Language Models
di: Yang, Zhenyuan, et al.
Pubblicazione: (2024)

Large Language Model Reasoning Failures
di: Song, Peiyang, et al.
Pubblicazione: (2026)

A Survey on Feedback-based Multi-step Reasoning for Large Language Models on Mathematics
di: Wei, Ting-Ruen, et al.
Pubblicazione: (2025)

ProtSAE: Disentangling and Interpreting Protein Language Models via Semantically-Guided Sparse Autoencoders
di: Liu, Xiangyu, et al.
Pubblicazione: (2025)

To Err Is Human: Systematic Quantification of Errors in Published AI Papers via LLM Analysis
di: Bianchi, Federico, et al.
Pubblicazione: (2025)

Analyzing Reasoning Consistency in Large Multimodal Models under Cross-Modal Conflicts
di: Zhu, Zhihao, et al.
Pubblicazione: (2026)

Can Large Language Models Analyze Graphs like Professionals? A Benchmark, Datasets and Models
di: Li, Xin, et al.
Pubblicazione: (2024)

Precedent-Informed Reasoning: Mitigating Overthinking in Large Reasoning Models via Test-Time Precedent Learning
di: Wang, Qianyue, et al.
Pubblicazione: (2026)

Detection and Mitigation of Hallucination in Large Reasoning Models: A Mechanistic Perspective
di: Sun, Zhongxiang, et al.
Pubblicazione: (2025)