Image de couverture de livre

Honest AI: Fine-Tuning "Small" Language Models to Say "I Don't Know", and Reducing Hallucination in RAG

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Xinxi, Wang, Li, Wu, Wei, Tang, Qi, Liu, Yiyao
Format:	Preprint
Publié:	2024
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

What Models Know, How Well They Know It: Knowledge-Weighted Fine-Tuning for Learning When to Say "I Don't Know"
par: Lee, Joosung, et autres
Publié: (2026)

R-Tuning: Instructing Large Language Models to Say `I Don't Know'
par: Zhang, Hanning, et autres
Publié: (2023)

Can AI Assistants Know What They Don't Know?
par: Cheng, Qinyuan, et autres
Publié: (2024)

Do Retrieval Augmented Language Models Know When They Don't Know?
par: Zhou, Youchao, et autres
Publié: (2025)

Large Language Models Must Be Taught to Know What They Don't Know
par: Kapoor, Sanyam, et autres
Publié: (2024)

Reasoning Models Don't Always Say What They Think
par: Chen, Yanda, et autres
Publié: (2025)

Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?
par: Mei, Zhiting, et autres
Publié: (2025)

Knowing You Don't Know: Learning When to Continue Search in Multi-round RAG through Self-Practicing
par: Yang, Diji, et autres
Publié: (2025)

Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
par: Madhwal, Dhruv, et autres
Publié: (2026)

Fine-Tuned LLMs Know They Don't Know: A Parameter-Efficient Approach to Recovering Honesty
par: Shi, Zeyu, et autres
Publié: (2025)

What Language Models Know But Don't Say: Non-Generative Prior Extraction for Generalization
par: Rezaeimanesh, Sara, et autres
Publié: (2026)

HonestLLM: Toward an Honest and Helpful Large Language Model
par: Gao, Chujie, et autres
Publié: (2024)

Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
par: Lv, Qitan, et autres
Publié: (2024)

Don't Fine-Tune, Decode: Syntax Error-Free Tool Use via Constrained Decoding
par: Zhang, Kexun, et autres
Publié: (2023)

Why Models Know But Don't Say: Chain-of-Thought Faithfulness Divergence Between Thinking Tokens and Answers in Open-Weight Reasoning Models
par: Young, Richard J.
Publié: (2026)

Fine-Tuning Language Models to Know What They Know
par: Park, Sangjun, et autres
Publié: (2026)

KnowTuning: Knowledge-aware Fine-tuning for Large Language Models
par: Lyu, Yougang, et autres
Publié: (2024)

Mini-Giants: "Small" Language Models and Open Source Win-Win
par: Zhou, Zhengping, et autres
Publié: (2023)

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models
par: Zhang, Yuxiang, et autres
Publié: (2024)

Language Models Don't Learn the Physical Manifestation of Language
par: Lee, Bruce W., et autres
Publié: (2024)

When Robots Should Say "I Don't Know": Benchmarking Abstention in Embodied Question Answering
par: Wu, Tao, et autres
Publié: (2025)

The Accuracy Paradox in RLHF: When Better Reward Models Don't Yield Better Language Models
par: Chen, Yanjun, et autres
Publié: (2024)

Fine-Tuned Large Language Models for Logical Translation: Reducing Hallucinations with Lang2Logic
par: Pan, Muyu, et autres
Publié: (2025)

Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
par: Vakharia, Priyesh, et autres
Publié: (2023)

Don't Let It Hallucinate: Premise Verification via Retrieval-Augmented Logical Reasoning
par: Qin, Yuehan, et autres
Publié: (2025)

Chip-Tuning: Classify Before Language Models Say
par: Zhu, Fangwei, et autres
Publié: (2024)

Noise Augmented Fine Tuning for Mitigating Hallucinations in Large Language Models
par: Khadangi, Afshin, et autres
Publié: (2025)

I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
par: Cohen, Roi, et autres
Publié: (2024)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
par: Ferrando, Javier, et autres
Publié: (2024)

Know3-RAG: A Knowledge-aware RAG Framework with Adaptive Retrieval, Generation, and Filtering
par: Liu, Xukai, et autres
Publié: (2025)

Measuring What VLMs Don't Say: Validation Metrics Hide Clinical Terminology Erasure in Radiology Report Generation
par: Parikh, Aditya, et autres
Publié: (2026)

Don't Say No: Jailbreaking LLM by Suppressing Refusal
par: Zhou, Yukai, et autres
Publié: (2024)

Can LLMs Ground when they (Don't) Know: A Study on Direct and Loaded Political Questions
par: Lachenmaier, Clara, et autres
Publié: (2025)

Removal of Hallucination on Hallucination: Debate-Augmented RAG
par: Hu, Wentao, et autres
Publié: (2025)

Don't Retrieve, Navigate: Distilling Enterprise Knowledge into Navigable Agent Skills for QA and RAG
par: Sun, Yiqun, et autres
Publié: (2026)

Don't Forget to Connect! Improving RAG with Graph-based Reranking
par: Dong, Jialin, et autres
Publié: (2024)

Don't Pay Attention
par: Hammoud, Mohammad, et autres
Publié: (2025)

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
par: Mayne, Harry, et autres
Publié: (2025)

BeHonest: Benchmarking Honesty in Large Language Models
par: Chern, Steffi, et autres
Publié: (2024)

Fine-Tune, Don't Prompt, Your Language Model to Identify Biased Language in Clinical Notes
par: Landi, Isotta, et autres
Publié: (2026)