paper-with-me

홈 › Papers

Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment

2026-05-31 · Hamidreza Hasani Balyani, Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi, Amin Gholami Davodi, Arshia Gharagozlou arxiv

Large language models are increasingly deployed as advisors whose objective is not aligned with the user's: recommenders optimize for engagement, sales assistants for purchases, negotiation agents for concessions. Whether such advisors stay truthful when honesty conflicts with their own payoff is a core alignment-evaluation question. We turn the canonical Crawford-Sobel cheap-talk model into a pre-specified benchmark for LLM honesty under preference misalignment. Cheap-talk theory predicts neither full revelation nor silence but coarse monotone partitions, with fewer informative intervals as preference conflict grows. A sender observes a state omega in [0,1], wants the receiver's action near omega+b, and sends one costless message to a receiver whose ideal action is omega. The design uses 5 bias levels, 3 prompt frames, a fixed low-temperature setting, and 200 states per cell: 12,000 sender calls. For the positive-bias grid b in {0.01,0.04,0.08,0.12} the exact most-informative partition sizes are 7,4,3,2, with oracle normalized mutual information 0.5294, 0.3268, 0.2205, 0.1829. Running the full design on four instruction-tuned models (GPT-4o, Claude Sonnet 4.5, Gemini 2.5 Flash-Lite, Llama-3.3-70B), we find all four over-reveal relative to the most-informative equilibrium by 1.8 to 4.2x: normalized mutual information stays at 0.78-0.94 where the oracle prescribes 0.18-0.53. Informativeness declines with bias as predicted but never approaches the strategic optimum; rather than coarse partitions, models show near-full revelation with a constant upward offset tracking their bias (linear exaggeration). Payoff-maximizing versus honesty framing has negligible effect. A decoder ablation shows the finding is recoverable only when the receiver reads the sender's stated number: an embedding-only decoder mis-reads the same data as near-babbling.

📄 PDF Abstract BibTeX arXiv:2606.01456

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GRATH: Gradual Self-Truthifying for Large Language Models

2024-01-22 · Weixin Chen, Dawn Song, Bo Li

Truthfulness is paramount for large language models (LLMs) as they are increasingly deployed in real-world applications. However, existing LLMs still struggle with generating truthful content, as evidenced by their modes…

TruthfulQA

TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space

2024-02-27 · Shaolei Zhang, Tian Yu, Yang Feng

Large Language Models (LLMs) sometimes suffer from producing hallucinations, especially LLMs may generate untruthful responses despite knowing the correct knowledge. Activating the truthfulness within LLM is the key to f…

Contrastive LearningHallucinationHallucination EvaluationLanguage Modelling+4

Truth Knows No Language: Evaluating Truthfulness Beyond English

2025-02-13 · Blanca Calvo Figueras, Eneko Sagarzazu, Julen Etxaniz, Jeremy Barnes 외

We introduce a professionally translated extension of the TruthfulQA benchmark designed to evaluate truthfulness in Basque, Catalan, Galician, and Spanish. Truthfulness evaluations of large language models (LLMs) have pr…

InformativenessMachine TranslationMultiple-choiceTranslation+1

KatotohananQA: Evaluating Truthfulness of Large Language Models in Filipino

2025-09-07 · Lorenzo Alfred Nery, Ronald Dawson Catignas, Thomas James Tiam-Lee arxiv

Large Language Models (LLMs) achieve remarkable performance across various tasks, but their tendency to produce hallucinations limits reliable adoption. Benchmarks such as TruthfulQA have been developed to measure truthf…

On The Truthfulness of 'Surprisingly Likely' Responses of Large Language Models

2023-11-13 · Naman Goel

The principle of rewarding a crowd for surprisingly common answers has been used in the literature for designing a number of truthful information elicitation mechanisms. A related method has also been proposed in the lit…

Language ModelingLanguage ModellingLarge Language ModelTruthfulQA