Copertina

Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tomani, Christian, Chaudhuri, Kamalika, Evtimov, Ivan, Cremers, Daniel, Ibrahim, Mark
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

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

Quality-Aware Translation Models: Efficient Generation and Quality Estimation in a Single Model
di: Tomani, Christian, et al.
Pubblicazione: (2023)

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

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

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

SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models
di: Gao, Xiang, et al.
Pubblicazione: (2024)

Safety Alignment of LMs via Non-cooperative Games
di: Paulus, Anselm, et al.
Pubblicazione: (2025)

HALT-RAG: A Task-Adaptable Framework for Hallucination Detection with Calibrated NLI Ensembles and Abstention
di: Goswami, Saumya, et al.
Pubblicazione: (2025)

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
di: Evtimov, Ivan, et al.
Pubblicazione: (2025)

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

Privacy-Preserving Retrieval-Augmented Generation with Differential Privacy
di: Koga, Tatsuki, et al.
Pubblicazione: (2024)

Second Guess: Detecting Uncertainty Through Abstention and Answer Stability in Small Language Models
di: Aravindan, Ashwath Vaithinathan, et al.
Pubblicazione: (2026)

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
di: Zharmagambetov, Arman, et al.
Pubblicazione: (2025)

Correction with Backtracking Reduces Hallucination in Summarization
di: Liu, Zhenzhen, et al.
Pubblicazione: (2023)

From Attribution to Abstention: Training-Free Attention-Based Auditing for Clinical Summarization
di: Yan, Qianqi, et al.
Pubblicazione: (2026)

Knowledge Graph Guided Evaluation of Abstention Techniques
di: Vasisht, Kinshuk, et al.
Pubblicazione: (2024)

Customizing Language Model Responses with Contrastive In-Context Learning
di: Gao, Xiang, et al.
Pubblicazione: (2024)

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

Improving Metacognition and Uncertainty Communication in Language Models
di: Steyvers, Mark, et al.
Pubblicazione: (2025)

Improving Training Efficiency and Reducing Maintenance Costs via Language Specific Model Merging
di: Dmonte, Alphaeus, et al.
Pubblicazione: (2026)

A Geometric Taxonomy of Hallucinations in LLMs
di: Marín, Javier
Pubblicazione: (2026)

Hallucination Detection with the Internal Layers of LLMs
di: Preiß, Martin
Pubblicazione: (2025)

Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection
di: Chen, Kedi, et al.
Pubblicazione: (2025)

Anthropomimetic Uncertainty: What Verbalized Uncertainty in Language Models is Missing
di: Ulmer, Dennis, et al.
Pubblicazione: (2025)

Hallucination is Inevitable for LLMs with the Open World Assumption
di: Xu, Bowen
Pubblicazione: (2025)

M-Wanda: Improving One-Shot Pruning for Multilingual LLMs
di: Choenni, Rochelle, et al.
Pubblicazione: (2025)

The Two Sides of the Coin: Hallucination Generation and Detection with LLMs as Evaluators for LLMs
di: Bui, Anh Thu Maria, et al.
Pubblicazione: (2024)

Triggering Hallucinations in LLMs: A Quantitative Study of Prompt-Induced Hallucination in Large Language Models
di: Sato, Makoto
Pubblicazione: (2025)

How Much Do LLMs Hallucinate across Languages? On Realistic Multilingual Estimation of LLM Hallucination
di: Islam, Saad Obaid ul, et al.
Pubblicazione: (2025)

AdvPrefix: An Objective for Nuanced LLM Jailbreaks
di: Zhu, Sicheng, et al.
Pubblicazione: (2024)

Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
di: Lv, Qitan, et al.
Pubblicazione: (2024)

Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
di: Wan, Yixin, et al.
Pubblicazione: (2023)

Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions
di: Atif, Farah, et al.
Pubblicazione: (2025)

SINdex: Semantic INconsistency Index for Hallucination Detection in LLMs
di: Abdaljalil, Samir, et al.
Pubblicazione: (2025)

Hallucination Detection in LLMs with Topological Divergence on Attention Graphs
di: Bazarova, Alexandra, et al.
Pubblicazione: (2025)

Can Hallucinations Help? Boosting LLMs for Drug Discovery
di: Yuan, Shuzhou, et al.
Pubblicazione: (2025)

RAG LLMs are Not Safer: A Safety Analysis of Retrieval-Augmented Generation for Large Language Models
di: An, Bang, et al.
Pubblicazione: (2025)

Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
di: Feng, Yujie, et al.
Pubblicazione: (2026)

Multi-Modal Fact-Verification Framework for Reducing Hallucinations in Large Language Models
di: Patel, Piyushkumar
Pubblicazione: (2025)

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