English
Related papers

Related papers: Lies, Labels, and Mechanisms

200 papers

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes…

Machine Learning · Computer Science 2019-06-25 Rohin Shah , Noah Gundotra , Pieter Abbeel , Anca D. Dragan

Eliciting reasoning has emerged as a powerful technique for improving the performance of large language models (LLMs) on complex tasks by inducing thinking. However, their effectiveness in realistic user-engaged agent scenarios remains…

Computation and Language · Computer Science 2026-02-10 Jiatong Li , Changdae Oh , Hyeong Kyu Choi , Jindong Wang , Sharon Li

Hallucination in large language models (LLMs) has been widely studied in recent years, with progress in both detection and mitigation aimed at improving truthfulness. Yet, a critical side effect remains largely overlooked: enhancing…

Computation and Language · Computer Science 2026-02-02 Omar Mahmoud , Ali Khalil , Buddhika Laknath Semage , Thommen George Karimpanal , Santu Rana

Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a model's self-assessment explicit: when the model is…

Machine Learning · Computer Science 2026-05-15 Junyu Guo , Shangding Gu , Ming Jin , Costas Spanos , Javad Lavaei

This paper studies the role of hard information in contractual and market settings in which the receiver can flexibly adjust allocations and transfers in response to the sender's disclosure. These settings include monopoly pricing,…

Theoretical Economics · Economics 2026-01-09 S. Nageeb Ali , Andreas Kleiner , Kun Zhang

Self-evolving agents offer a promising path toward scalable autonomy. However, in this work, we show that in competitive environments, self-evolution can instead give rise to a serious and previously underexplored risk: the spontaneous…

Cryptography and Security · Computer Science 2026-03-16 Zonghao Ying , Haowen Dai , Tianyuan Zhang , Yisong Xiao , Quanchen Zou , Aishan Liu , Jian Yang , Yaodong Yang , Xianglong Liu

Language models (LMs) are increasingly used in high-stakes, multi-agent settings, where following instructions and maintaining value alignment are critical. Most alignment research focuses on interactions between a single LM and a single…

Artificial Intelligence · Computer Science 2026-05-12 Maria Chang , Ronny Luss , Miao Liu , Keerthiram Murugesan , Karthikeyan Ramamurthy , Djallel Bouneffouf

Large Language Models (LLMs) are intended to reflect human linguistic competencies. But humans have access to a broad and embodied context, which is key in detecting and resolving linguistic ambiguities, even in isolated text spans. A…

Computation and Language · Computer Science 2025-10-22 Amber Shore , Russell Scheinberg , Ameeta Agrawal , So Young Lee

As agentic AI becomes more widespread, agents with distinct and possibly conflicting goals will interact in complex ways. These multi-agent interactions pose a fundamental challenge, particularly in social dilemmas, where agents' individual…

Machine Learning · Computer Science 2025-12-02 Dereck Piche , Mohammed Muqeeth , Milad Aghajohari , Juan Duque , Michael Noukhovitch , Aaron Courville

Motivated by growing evidence of agents' mistakes in strategically simple environments, we propose a solution concept -- robust equilibrium -- that requires only an asymptotically optimal behavior. We use it to study large random matching…

Theoretical Economics · Economics 2023-09-26 Georgy Artemov , Yeon-Koo Che , YingHua He

Training against white-box deception detectors has been proposed as a way to make AI systems honest. However, such training risks models learning to obfuscate their deception to evade the detector. Prior work has studied obfuscation only in…

Machine Learning · Computer Science 2026-05-28 Mohammad Taufeeque , Stefan Heimersheim , Adam Gleave , Chris Cundy

Agentic workflows -- where multiple large language model (LLM) instances interact to solve tasks -- are increasingly built on feedback mechanisms, where one model evaluates and critiques another. Despite the promise of feedback-driven…

Artificial Intelligence · Computer Science 2025-06-05 Yifei Ming , Zixuan Ke , Xuan-Phi Nguyen , Jiayu Wang , Shafiq Joty

We design and implement lab experiments to evaluate the normative appeal of behavior arising from models of ambiguity-averse preferences. We report two main empirical findings. First, we demonstrate that behavior reflects an incomplete…

Theoretical Economics · Economics 2024-07-26 Christoph Kuzmics , Brian W. Rogers , Xiannong Zhang

Large language models (LLMs) inherit biases from their training data and alignment processes, influencing their responses in subtle ways. While many studies have examined these biases, little work has explored their robustness during…

Computation and Language · Computer Science 2024-11-06 Virgile Rennard , Christos Xypolopoulos , Michalis Vazirgiannis

Large Language Models (LLMs) are effective at deceiving, when prompted to do so. But under what conditions do they deceive spontaneously? Models that demonstrate better performance on reasoning tasks are also better at prompted deception.…

Computation and Language · Computer Science 2025-04-02 Samuel M. Taylor , Benjamin K. Bergen

We consider a task of scheduling with a common deadline on a single machine. Every player reports to a scheduler the length of his job and the scheduler needs to finish as many jobs as possible by the deadline. For this simple problem,…

Computer Science and Game Theory · Computer Science 2011-03-15 Uriel Feige , Moshe Tennenholtz

Are large language models (LLMs) biased in favor of communications produced by LLMs, leading to possible antihuman discrimination? Using a classical experimental design inspired by employment discrimination studies, we tested widely used…

Computation and Language · Computer Science 2025-08-12 Walter Laurito , Benjamin Davis , Peli Grietzer , Tomáš Gavenčiak , Ada Böhm , Jan Kulveit

Recent work characterizing the optimal performance of secrecy systems has made use of a distortion-like metric for partial secrecy as a replacement for the more traditional metric of equivocation. In this work we use the log-loss function…

Information Theory · Computer Science 2013-03-12 Paul Cuff

A binary classifier capable of abstaining from making a label prediction has two goals in tension: minimizing errors, and avoiding abstaining unnecessarily often. In this work, we exactly characterize the best achievable tradeoff between…

Machine Learning · Computer Science 2016-11-30 Akshay Balsubramani

The rapid proliferation of recent Multi-Agent Systems (MAS), where Large Language Models (LLMs) and Large Reasoning Models (LRMs) usually collaborate to solve complex problems, necessitates a deep understanding of the persuasion dynamics…

Artificial Intelligence · Computer Science 2025-09-26 Haodong Zhao , Jidong Li , Zhaomin Wu , Tianjie Ju , Zhuosheng Zhang , Bingsheng He , Gongshen Liu