Pith. sign in

REVIEW 5 cited by

A Survey on the Honesty of Large Language Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2409.18786 v1 pith:CPSG5ZIQ submitted 2024-09-27 cs.CL cs.AI

Siheng Li , Cheng Yang , Taiqiang Wu , Chufan Shi , Yuji Zhang , Xinyu Zhu , Zesen Cheng , Deng Cai
show 7 more authors
Mo Yu Lemao Liu Jie Zhou Yujiu Yang Ngai Wong Xixin Wu Wai Lam
This is my paper · ORCID
classification cs.CLcs.AI
keywords honestyllmsknowmodelsresearchexpressknowledgelanguage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Honesty is a fundamental principle for aligning large language models (LLMs) with human values, requiring these models to recognize what they know and don't know and be able to faithfully express their knowledge. Despite promising, current LLMs still exhibit significant dishonest behaviors, such as confidently presenting wrong answers or failing to express what they know. In addition, research on the honesty of LLMs also faces challenges, including varying definitions of honesty, difficulties in distinguishing between known and unknown knowledge, and a lack of comprehensive understanding of related research. To address these issues, we provide a survey on the honesty of LLMs, covering its clarification, evaluation approaches, and strategies for improvement. Moreover, we offer insights for future research, aiming to inspire further exploration in this important area.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MMOOC: A Comprehensive Benchmark for Out-of-Context Evaluation in Multimodal Large Language Models

    cs.CV 2026-07 conditional novelty 6.0 of 10

    MMOOC, a 41K-pair benchmark, shows current multimodal LLMs struggle to both refuse truly out-of-context questions and correctly answer questions that remain answerable despite misleading or shifted context.

  2. UAQFact: Evaluating Factual Knowledge Utilization of LLMs on Unanswerable Questions

    cs.CL 2025-05 conditional novelty 6.0 of 10

    A new bilingual benchmark ties unanswerable questions to Wikidata facts and shows that LLMs often store the relevant knowledge yet fail to use it to recognize unanswerability.

  3. GRAIT: Gradient-Driven Refusal-Aware Instruction Tuning for Effective Hallucination Mitigation

    cs.CL 2025-02 conditional novelty 6.0 of 10

    GRAIT selects and reweights refusal-training examples using gradient influence, reporting lower hallucination rates and better helpfulness scores than prior refusal-aware tuning baselines.

  4. UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models

    cs.CL 2024-12 conditional novelty 6.0 of 10

    UAlign improves LLM factuality alignment by adding predicted confidence and semantic entropy as input features to prompts and the reward model, helping the model answer known questions and refuse unknown ones.

  5. Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges

    cs.AI 2025-07 reject novelty 1.0 of 10

    A broad survey of LLM alignment that catalogs objectives, benchmarks, SFT/RLHF/DPO methods, and safety challenges, without contributing new experimental or theoretical results.

Pith tools