Seyed Pouyan Mousavi Davoudi
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1NLP×1Game Theory×1
Frequent co-authors
Research Timeline
2026
Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
The paper establishes a benchmark based on the cheap-talk model to test LLM honesty when their incentives conflict with the user's, finding that models consistently over-reveal information regardless of the bias level.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CLcs.GTRecentMay 31, 2026
Truthful AI Advisors: A Pre-Specified Benchmark for Large Language Model Honesty Under Preference Misalignment
Hamidreza Hasani Balyani, Seyed Pouyan Mousavi Davoudi, Alireza Amiri-Margavi, Amin Gholami Davodi +1 more
The paper establishes a benchmark based on the cheap-talk model to test LLM honesty when their incentives conflict with the user's, finding that models consistently over-reveal information regardless…
View →