paper-with-me

Papers

Alignment for Honesty

2023-12-12 · Yuqing Yang, Ethan Chern, Xipeng Qiu, Graham Neubig, PengFei Liu

Recent research has made significant strides in aligning large language models (LLMs) with helpfulness and harmlessness. In this paper, we argue for the importance of alignment for \emph{honesty}, ensuring that LLMs proactively refuse to answer questions when they lack knowledge, while still not being overly conservative. However, a pivotal aspect of alignment for honesty involves discerning an LLM's knowledge boundaries, which demands comprehensive solutions in terms of metric development, benchmark creation, and training methodologies. We address these challenges by first establishing a precise problem definition and defining ``honesty'' inspired by the Analects of Confucius. This serves as a cornerstone for developing metrics that effectively measure an LLM's honesty by quantifying its progress post-alignment. Furthermore, we introduce a flexible training framework which is further instantiated by several efficient fine-tuning techniques that emphasize honesty without sacrificing performance on other tasks. Our extensive experiments reveal that these aligned models show a marked increase in honesty, as indicated by our proposed metrics. We open-source all relevant resources to facilitate future research at \url{https://github.com/GAIR-NLP/alignment-for-honesty}.

📄 PDF Abstract BibTeX arXiv:2312.07000

Code (1)

gair-nlp/alignment-for-honesty 공식 구현

Similar Papers 제목 키워드 기반

Dishonesty in Helpful and Harmless Alignment

2024-06-04 · Youcheng Huang, Jingkun Tang, Duanyu Feng, Zheng Zhang 외

People tell lies when seeking rewards. Large language models (LLMs) are aligned to human values with reinforcement learning where they get rewards if they satisfy human preference. We find that this also induces dishones…

Annotation-Efficient Universal Honesty Alignment

2025-10-20 · Shiyu Ni, Keping Bi, Jiafeng Guo, Minghao Tang 외 arxiv

Honesty alignment-the ability of large language models (LLMs) to recognize their knowledge boundaries and express calibrated confidence-is essential for trustworthy deployment. Existing methods either rely on training-fr…

BeHonest: Benchmarking Honesty in Large Language Models

2024-06-19 · Steffi Chern, Zhulin Hu, Yuqing Yang, Ethan Chern 외

Previous works on Large Language Models (LLMs) have mainly focused on evaluating their helpfulness or harmlessness. However, honesty, another crucial alignment criterion, has received relatively less attention. Dishonest…

BenchmarkingMisinformation

MoHoBench: Assessing Honesty of Multimodal Large Language Models via Unanswerable Visual Questions

2025-07-29 · Yanxu Zhu, Shitong Duan, Xiangxu Zhang, Jitao Sang 외 arxiv

Recently Multimodal Large Language Models (MLLMs) have achieved considerable advancements in vision-language tasks, yet produce potentially harmful or untrustworthy content. Despite substantial work investigating the tru…

LLMs Deceive Unintentionally: Emergent Misalignment in Dishonesty from Misaligned Samples to Biased Human-AI Interactions

2025-10-09 · Xuhao Hu, Peng Wang, Xiaoya Lu, Dongrui Liu 외 arxiv

Previous research has shown that LLMs finetuned on malicious or incorrect completions within narrow domains (e.g., insecure code or incorrect medical advice) can become broadly misaligned to exhibit harmful behaviors, wh…