arXiv Computation and Language
The Confidence Game: Strategic Miscalibration in Human-AI Delegation
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Aug 26
Confident at the moment of action: belief miscalibration in LLM play under hidden information
The paper investigates whether large language models (LLMs) correctly gauge their confidence when acting in a hidden‑information chess variant. In experiments where the location of a hidden royal piece is repeatedly relocated, the models’ stated probabilities about the piece’s position were almost never accurate at high confidence levels, with a calibration deficit concentrated in those high‑confidence events. Across multiple model configurations and providers, the same pattern emerged, and conventional evaluation metrics such as legality, cost, latency, and completion rate were found to be uncorrelated with belief quality, yet a model could still win the game despite poor confidence estimates.
Hugging Face Trending Papers
Aug 25
Confident at the moment of action: belief miscalibration in LLM play under hidden information
Agentic systems increasingly gate actions on a model's own stated confidence, which assumes confidence tracks correctness at the moment of acting. We test this in a hidden-information chess variant wh...
arXiv AI
Jun 30
Safety from Honesty in a Disinterested AI Predictor
arXiv:2606. 29657v1 Announce Type: new Abstract: As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified.
Hugging Face Trending Papers
Jun 28
Safety from Honesty in a Disinterested AI Predictor
As AI systems become more capable, training procedures that optimize for downstream outcomes risk introducing implicit agency: goal-directed behavior that designers never specified. We present a formal safety argument for the Scientist AI (SAI) Predictor, trained to approximate the Bayesian posterior conditioned on a dataset of "epistemically contextualized" natural-language statements.
arXiv Computation and Language
1d ago
Game-Theoretic Solvers with Bayesian Opponent Modeling and Moral Rhetoric Framing for GLEE
The paper presents an agent designed for the GLEE Competition that engages in bargaining, negotiation, and persuasion games against human and AI opponents. The agent combines a classical game‑theoretic solver, an online Bayesian layer for estimating opponent archetypes, and a language model for generating messages. Experiments include 13,200 Monte Carlo games against 11 synthetic archetypes, an ablation study of the opponent‑modeling layer, and an analysis of 9,337 live‑game messages showing a strong correlation between moral rhetoric framing and buyer purchase decisions.
arXiv AI
2d ago
When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems
arXiv:2610.33011v1 Announce Type: cross Abstract: While recent advances in autonomous agents enable them to coordinate on increasingly complex tasks, prior work shows that this growing capacity for c...