English
Related papers

Related papers: Lies, Labels, and Mechanisms

200 papers

LLM-based agents increasingly coordinate decisions in multi-agent systems, often attaching natural-language reasoning to actions. However, reasoning is neither free nor automatically reliable: it incurs computational cost and, without…

Multiagent Systems · Computer Science 2026-04-14 Feliks Bańka , Jarosław A. Chudziak

Activation engineering is becoming increasingly popular as a means of online control of large language models (LLMs). In this work, we extend the idea of inference-time steering with vectors that represent a behavioral direction of interest…

Machine Learning · Computer Science 2024-11-26 Christopher M. Ackerman

Large Language Models (LLMs) have been shown to achieve impressive results for many reasoning-based NLP tasks, suggesting a degree of deductive reasoning capability. However, it remains unclear to which extent LLMs, in both informal and…

Computation and Language · Computer Science 2025-08-26 Fabian Hoppe , Filip Ilievski , Jan-Christoph Kalo

The feedback data of recommender systems are often subject to what was exposed to the users; however, most learning and evaluation methods do not account for the underlying exposure mechanism. We first show in theory that applying…

Information Retrieval · Computer Science 2020-12-07 Da Xu , Chuanwei Ruan , Evren Korpeoglu , Sushant Kumar , Kannan Achan

Counterfactual examples are widely employed to enhance the performance and robustness of large language models (LLMs) through counterfactual data augmentation (CDA). However, the selection of the judge model used to evaluate label flipping,…

Computation and Language · Computer Science 2025-08-28 Qianli Wang , Van Bach Nguyen , Nils Feldhus , Luis Felipe Villa-Arenas , Christin Seifert , Sebastian Möller , Vera Schmitt

We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of prompts that are…

Computation and Language · Computer Science 2026-01-27 Jan Betley , Daniel Tan , Niels Warncke , Anna Sztyber-Betley , Xuchan Bao , Martín Soto , Nathan Labenz , Owain Evans

Metacognition -- assessing the quality of one's own cognitive performance -- guides adaptive behavior across species. Substantial research demonstrates that confidence signals can be extracted from language model outputs, yet a fundamental…

Machine Learning · Computer Science 2026-05-20 Dharshan Kumaran , Nathaniel Daw , Simon Osindero , Petar Veličković , Viorica Patraucean

Large language models (LLMs) increasingly mediate economic and organisational processes, from automated customer support and recruitment to investment advice and policy analysis. These systems are often assumed to embody rational decision…

General Economics · Economics 2025-11-18 Luca Corazzini , Elisa Deriu , Marco Guerzoni

We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about this behavior without being instructed to do so. Concretely,…

Computation and Language · Computer Science 2024-07-16 Jérémy Scheurer , Mikita Balesni , Marius Hobbhahn

The fairness and trustworthiness of Large Language Models (LLMs) are receiving increasing attention. Implicit hate speech, which employs indirect language to convey hateful intentions, occupies a significant portion of practice. However,…

Computation and Language · Computer Science 2024-07-24 Min Zhang , Jianfeng He , Taoran Ji , Chang-Tien Lu

Acquiescence bias, i.e. the tendency of humans to agree with statements in surveys, independent of their actual beliefs, is well researched and documented. Since Large Language Models (LLMs) have been shown to be very influenceable by…

Computation and Language · Computer Science 2025-09-11 Daniel Braun

In traditional mechanism design, agents only care about the utility they derive from the outcome of the mechanism. We look at a richer model where agents also assign non-negative dis-utility to the information about their private types…

Computer Science and Game Theory · Computer Science 2015-03-19 Kobbi Nissim , Claudio Orlandi , Rann Smorodinsky

Recent advances in applying reinforcement learning (RL) to large language models (LLMs) have led to substantial progress. In particular, a series of remarkable yet often counterintuitive phenomena have been reported in LLMs, exhibiting…

Machine Learning · Computer Science 2025-09-03 Haoze Wu , Cheng Wang , Wenshuo Zhao , Junxian He

As large language models (LLMs) become more integrated into societal systems, the risk of them perpetuating and amplifying harmful biases becomes a critical safety concern. Traditional methods for mitigating bias often rely on data…

Artificial Intelligence · Computer Science 2025-08-13 Shivam Dubey

Large-language models are capable of completing a variety of tasks, but remain unpredictable and intractable. Representation engineering seeks to resolve this problem through a new approach utilizing samples of contrasting inputs to detect…

Artificial Intelligence · Computer Science 2025-02-26 Lukasz Bartoszcze , Sarthak Munshi , Bryan Sukidi , Jennifer Yen , Zejia Yang , David Williams-King , Linh Le , Kosi Asuzu , Carsten Maple

Reasoning models have attracted increasing attention for their ability to tackle complex tasks, embodying the System II (slow thinking) paradigm in contrast to System I (fast, intuitive responses). Yet a key question remains: Does slower…

Artificial Intelligence · Computer Science 2026-04-17 Sitong Fang , Wenjing Cao , Jiahao Li , Xuyao Wang , Juntao Dai , Chi-Min Chan , Sirui Han , Yike Guo , Yaodong Yang , Jiaming Ji

We introduce the notion of fault tolerant mechanism design, which extends the standard game theoretic framework of mechanism design to allow for uncertainty about execution. Specifically, we define the problem of task allocation in which…

Computer Science and Game Theory · Computer Science 2013-01-07 Ryan Porter , Amir Ronen , Yoav Shoham , Moshe Tennenholtz

This paper studies the organization of communication between biased senders and a receiver. Senders can misreport their private information at a cost. Efficiency is achieved by clearing information asymmetries without incurring costs.…

Theoretical Economics · Economics 2025-02-04 Federico Vaccari

Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (e.g., gender or race). We instead argue that a favorable debiasing method should use sensitive information 'fairly,' with…

Computation and Language · Computer Science 2023-10-24 Bodhisattwa Prasad Majumder , Zexue He , Julian McAuley

Large language models (LLMs) are increasingly used as proxies for human judgment in computational social science, yet their ability to reproduce patterns of susceptibility to misinformation remains unclear. We test whether LLM-simulated…

Social and Information Networks · Computer Science 2026-04-13 Eun Cheol Choi , Lindsay E. Young , Emilio Ferrara