Copertina

Thinking, Faithful and Stable: Mitigating Hallucinations in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Zou, Chelsea, Yao, Yiheng, Khalil, Basant
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

CalBench: Evaluating Coordination-Privacy Trade-offs in Multi-Agent LLMs
di: Zou, Chelsea, et al.
Pubblicazione: (2026)

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation
di: Yao, Yiheng, et al.
Pubblicazione: (2026)

One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs
di: Wang, Pengbo, et al.
Pubblicazione: (2025)

FaithLens: Detecting and Explaining Faithfulness Hallucination
di: Si, Shuzheng, et al.
Pubblicazione: (2025)

FaithBench: A Diverse Hallucination Benchmark for Summarization by Modern LLMs
di: Bao, Forrest Sheng, et al.
Pubblicazione: (2024)

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding
di: Xu, Zhongxing, et al.
Pubblicazione: (2026)

INFACT: A Diagnostic Benchmark for Induced Faithfulness and Factuality Hallucinations in Video-LLMs
di: Yang, Junqi, et al.
Pubblicazione: (2026)

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
di: Xiong, Zidi, et al.
Pubblicazione: (2025)

Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges
di: Lee, Yunseo, et al.
Pubblicazione: (2025)

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs
di: Sun, Zhongxiang, et al.
Pubblicazione: (2026)

What LLMs Think When You Don't Tell Them What to Think About?
di: Kwon, Yongchan, et al.
Pubblicazione: (2026)

Hallucination Detection and Hallucination Mitigation: An Investigation
di: Luo, Junliang, et al.
Pubblicazione: (2024)

From Faithfulness to Correctness: Generative Reward Models that Think Critically
di: Ma, Qiyao, et al.
Pubblicazione: (2025)

Self-Alignment for Factuality: Mitigating Hallucinations in LLMs via Self-Evaluation
di: Zhang, Xiaoying, et al.
Pubblicazione: (2024)

On the Faithfulness of Visual Thinking: Measurement and Enhancement
di: Liu, Zujing, et al.
Pubblicazione: (2025)

Acting with AI: An Interaction-Based Framework for Agentic Tort Liability
di: Yao, Yiheng
Pubblicazione: (2026)

Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMs
di: Lin, Chenchen, et al.
Pubblicazione: (2026)

Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination
di: Zheng, Haojie, et al.
Pubblicazione: (2024)

FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering
di: Tong, Chaodong, et al.
Pubblicazione: (2026)

MIH-TCCT: Mitigating Inconsistent Hallucinations in LLMs via Event-Driven Text-Code Cyclic Training
di: You, Xinxin, et al.
Pubblicazione: (2025)

Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data
di: Su, Yiheng, et al.
Pubblicazione: (2023)

On A Scale From 1 to 5: Quantifying Hallucination in Faithfulness Evaluation
di: Jing, Xiaonan, et al.
Pubblicazione: (2024)

DeFacto: Counterfactual Thinking with Images for Enforcing Evidence-Grounded and Faithful Reasoning
di: Xu, Tianrun, et al.
Pubblicazione: (2025)

ResNetVLLM-2: Addressing ResNetVLLM's Multi-Modal Hallucinations
di: Khalil, Ahmad, et al.
Pubblicazione: (2025)

Mitigating Gender Bias via Fostering Exploratory Thinking in LLMs
di: Wei, Kangda, et al.
Pubblicazione: (2025)

Faithfulness Serum: Mitigating the Faithfulness Gap in Textual Explanations of LLM Decisions via Attribution Guidance
di: Alon, Bar, et al.
Pubblicazione: (2026)

Hallucination Detection and Mitigation in Large Language Models
di: Pesaranghader, Ahmad, et al.
Pubblicazione: (2026)

Faithful or Just Plausible? Evaluating the Faithfulness of Closed-Source LLMs in Medical Reasoning
di: Afolabi, Halimat, et al.
Pubblicazione: (2026)

Faithful-First Reasoning, Planning, and Acting for Multimodal LLMs
di: Li, Junxian, et al.
Pubblicazione: (2025)

Dissociation of Faithful and Unfaithful Reasoning in LLMs
di: Yee, Evelyn, et al.
Pubblicazione: (2024)

What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
di: Kim, Junho, et al.
Pubblicazione: (2024)

KARL: Mitigating Hallucinations in LLMs via Knowledge-Boundary-Aware Reinforcement Learning
di: Gao, Cheng, et al.
Pubblicazione: (2026)

Disentangling Deception and Hallucination Failures in LLMs
di: Lu, Haolang, et al.
Pubblicazione: (2026)

Think Before Refusal : Triggering Safety Reflection in LLMs to Mitigate False Refusal Behavior
di: Si, Shengyun, et al.
Pubblicazione: (2025)

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
di: Shen, Xu, et al.
Pubblicazione: (2025)

SFR-RAG: Towards Contextually Faithful LLMs
di: Nguyen, Xuan-Phi, et al.
Pubblicazione: (2024)

MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
di: Jia, Ao, et al.
Pubblicazione: (2025)

CCL-XCoT: An Efficient Cross-Lingual Knowledge Transfer Method for Mitigating Hallucination Generation
di: Zheng, Weihua, et al.
Pubblicazione: (2025)

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

Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems
di: Li, Yihan, et al.
Pubblicazione: (2025)