English
Related papers

Related papers: Dishonesty in Helpful and Harmless Alignment

200 papers

Reinforcement learning from human feedback (RLHF) has emerged as a powerful technique to make large language models (LLMs) more capable in complex settings. RLHF proceeds as collecting human preference data, training a reward model on said…

Machine Learning · Computer Science 2024-02-05 Nathan Lambert , Roberto Calandra

Large Language Models (LLMs) are increasingly used to simulate human users in interactive settings such as therapy, education, and social role-play. While these simulations enable scalable training and evaluation of AI agents, off-the-shelf…

Computation and Language · Computer Science 2025-11-04 Marwa Abdulhai , Ryan Cheng , Donovan Clay , Tim Althoff , Sergey Levine , Natasha Jaques

Large language models (LLMs) are capable of generating plausible explanations of how they arrived at an answer to a question. However, these explanations can misrepresent the model's "reasoning" process, i.e., they can be unfaithful. This,…

Computation and Language · Computer Science 2025-05-21 Katie Matton , Robert Osazuwa Ness , John Guttag , Emre Kıcıman

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

Despite their widespread use in fact-checking, moderation, and high-stakes decision-making, large language models (LLMs) remain poorly understood as judges of truth. This study presents the largest evaluation to date of LLMs' veracity…

Computation and Language · Computer Science 2025-09-30 Emilio Barkett , Olivia Long , Madhavendra Thakur

Large Language Models (LLMs) are increasingly used in decision-making scenarios that involve risk assessment, yet their alignment with human economic rationality remains unclear. In this study, we investigate whether LLMs exhibit risk…

General Economics · Economics 2025-09-16 Jiaxin Liu , Yixuan Tang , Yi Yang , Kar Yan Tam

Large language models (LLMs) are increasingly used in modern search and answer systems to synthesize multiple, sometimes conflicting, texts into a single response, yet current pipelines offer weak incentives for sources to be accurate and…

Computation and Language · Computer Science 2026-02-26 Yanchen Jiang , Zhe Feng , Aranyak Mehta

In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like sycophancy to…

Large Language Models (LLMs) behave non-deterministically, and prompting has become a common method for steering their outputs. A popular strategy is to assign a persona to the model to produce more varied, context-sensitive responses,…

Computation and Language · Computer Science 2026-04-21 Bruce W. Lee , Yeongheon Lee , Hyunsoo Cho

Large Language Models (LLMs) are increasingly regarded as having the potential to generate persuasive content at scale. While previous studies have focused on the risks associated with LLM-generated misinformation, the role of LLMs in…

Computers and Society · Computer Science 2026-04-06 John Caffier , Olga Stavrova , Bennett Kleinberg

Current literature suggests that alignment faking (deceptive alignment) is an emergent property of large language models. We present the first empirical evidence that a small instruction-tuned model, specifically LLaMA 3 8B, can exhibit…

Computation and Language · Computer Science 2025-10-27 Jeanice Koorndijk

Human cognition, driven by complex neurochemical processes, oscillates between imagination and reality and learns to self-correct whenever such subtle drifts lead to hallucinations or unsafe associations. In recent years, LLMs have…

Computation and Language · Computer Science 2026-01-09 Sharanya Dasgupta , Arkaprabha Basu , Sujoy Nath , Swagatam Das

Large language models (LLMs) can "lie", which we define as outputting false statements despite "knowing" the truth in a demonstrable sense. LLMs might "lie", for example, when instructed to output misinformation. Here, we develop a simple…

Computation and Language · Computer Science 2023-09-28 Lorenzo Pacchiardi , Alex J. Chan , Sören Mindermann , Ilan Moscovitz , Alexa Y. Pan , Yarin Gal , Owain Evans , Jan Brauner

Large Language Models (LLMs) exhibit surprisingly diverse risk preferences when acting as AI decision makers, a crucial characteristic whose origins remain poorly understood despite their expanding economic roles. We analyze 50 LLMs using…

General Economics · Economics 2025-06-11 Shumiao Ouyang , Hayong Yun , Xingjian Zheng

Role-play in large language models (LLMs) enhances their ability to generate contextually relevant and high-quality responses by simulating diverse cognitive perspectives. However, our study identifies significant risks associated with this…

Computation and Language · Computer Science 2025-02-04 Jinman Zhao , Zifan Qian , Linbo Cao , Yining Wang , Yitian Ding , Yulan Hu , Zeyu Zhang , Zeyong Jin

Large language models (LLMs) may exhibit unintended or undesirable behaviors. Recent works have concentrated on aligning LLMs to mitigate harmful outputs. Despite these efforts, some anomalies indicate that even a well-conducted alignment…

Computation and Language · Computer Science 2025-09-24 Jiaming Ji , Kaile Wang , Tianyi Qiu , Boyuan Chen , Jiayi Zhou , Changye Li , Hantao Lou , Juntao Dai , Yunhuai Liu , Yaodong Yang

Large Language Models (LLMs) are deployed as powerful tools for several natural language processing (NLP) applications. Recent works show that modern LLMs can generate self-explanations (SEs), which elicit their intermediate reasoning steps…

Computation and Language · Computer Science 2024-03-15 Chirag Agarwal , Sree Harsha Tanneru , Himabindu Lakkaraju

"LLM-as-a-judge," which utilizes large language models (LLMs) as evaluators, has proven effective in many evaluation tasks. However, evaluator LLMs exhibit numerical bias, a phenomenon where certain evaluation scores are generated…

Computation and Language · Computer Science 2026-01-27 Ayako Sato , Hwichan Kim , Zhousi Chen , Masato Mita , Mamoru Komachi

Recent advances in Large Language Models (LLMs) have incorporated planning and reasoning capabilities, enabling models to outline steps before execution and provide transparent reasoning paths. This enhancement has reduced errors in…

Computation and Language · Computer Science 2025-01-31 Sudarshan Kamath Barkur , Sigurd Schacht , Johannes Scholl

Despite their impressive capabilities, Large Language Models (LLMs) exhibit unwanted uncertainty, a phenomenon where a model changes a previously correct answer into an incorrect one when re-prompted. This behavior undermines trust and…

Computation and Language · Computer Science 2025-10-28 Tiasa Singha Roy , Ayush Rajesh Jhaveri , Ilias Triantafyllopoulos