English
Related papers

Related papers: Strong Preferences Affect the Robustness of Prefer…

200 papers

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a…

As large language models (LLMs) become increasingly embedded in everyday applications, ensuring their alignment with the diverse preferences of individual users has become a critical challenge. Currently deployed approaches typically assume…

Machine Learning · Computer Science 2024-12-19 Katarzyna Kobalczyk , Claudio Fanconi , Hao Sun , Mihaela van der Schaar

Standard methods for aligning large language models with human preferences learn from pairwise comparisons among sampled candidate responses and regularize toward a reference policy. Despite their effectiveness, the effects of sampling and…

Machine Learning · Computer Science 2026-02-13 Yurong Chen , Yu He , Michael I. Jordan , Fan Yao

Reward models (RMs) are central to aligning large language models (LLMs) with human values but have received less attention than pretrained and post-trained LLMs themselves. Because RMs are initialized from LLMs, they inherit…

The emergence of large language models (LLMs) has opened up exciting possibilities for simulating human behavior and cognitive processes, with potential applications in various domains, including marketing research and consumer behavior…

Computation and Language · Computer Science 2024-11-13 Behnam Mohammadi

Pluralistic alignment has emerged as a critical frontier in the development of Large Language Models (LLMs), with reward models (RMs) serving as a central mechanism for capturing diverse human values. While benchmarks for general response…

Computation and Language · Computer Science 2026-04-09 Qiyao Ma , Dechen Gao , Rui Cai , Boqi Zhao , Hanchu Zhou , Junshan Zhang , Zhe Zhao

This paper examines the challenges associated with achieving life-long superalignment in AI systems, particularly large language models (LLMs). Superalignment is a theoretical framework that aspires to ensure that superintelligent AI…

Computers and Society · Computer Science 2024-03-25 Gokul Puthumanaillam , Manav Vora , Pranay Thangeda , Melkior Ornik

Aligning large language models (LLMs) to preference data typically assumes a known link function between observed preferences and latent rewards (e.g., a logistic Bradley-Terry link). Misspecification of this link can bias inferred rewards…

Machine Learning · Computer Science 2026-02-03 Nathan Kallus

Polite speech poses a fundamental alignment challenge for large language models (LLMs). Humans deploy a rich repertoire of linguistic strategies to balance informational and social goals -- from positive approaches that build rapport…

Computation and Language · Computer Science 2025-10-31 Haoran Zhao , Robert D. Hawkins

Large language Models (LLMs) are highly sensitive to variations in prompt formulation, which can significantly impact their ability to generate accurate responses. In this paper, we introduce a new task, Prompt Sensitivity Prediction, and a…

Computation and Language · Computer Science 2025-02-11 Amirhossein Razavi , Mina Soltangheis , Negar Arabzadeh , Sara Salamat , Morteza Zihayat , Ebrahim Bagheri

As Large Language Models (LLMs) continue to gain popularity due to their human-like traits and the intimacy they offer to users, their societal impact inevitably expands. This leads to the rising necessity for comprehensive studies to fully…

Artificial Intelligence · Computer Science 2025-01-07 Bojana Bodroza , Bojana M. Dinic , Ljubisa Bojic

Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of…

Artificial Intelligence · Computer Science 2025-11-18 Jea Kwon , Luiz Felipe Vecchietti , Sungwon Park , Meeyoung Cha

Aligning large language models with human preferences is critical for creating reliable and controllable AI systems. A human preference can be visualized as a high-dimensional vector where different directions represent trade-offs between…

Computation and Language · Computer Science 2026-02-26 Ruochen Mao , Yuling Shi , Xiaodong Gu , Jiaheng Wei

Large Language Models (LLMs) are often misleadingly recognized as having a personality or a set of values. We argue that an LLM can be seen as a superposition of perspectives with different values and personality traits. LLMs exhibit…

Computation and Language · Computer Science 2023-11-08 Grgur Kovač , Masataka Sawayama , Rémy Portelas , Cédric Colas , Peter Ford Dominey , Pierre-Yves Oudeyer

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act…

Artificial Intelligence · Computer Science 2021-03-16 Duncan C McElfresh , Lok Chan , Kenzie Doyle , Walter Sinnott-Armstrong , Vincent Conitzer , Jana Schaich Borg , John P Dickerson

Preference alignment in Large Language Models (LLMs) has significantly improved their ability to adhere to human instructions and intentions. However, existing direct alignment algorithms primarily focus on relative preferences and often…

Machine Learning · Computer Science 2025-05-13 Shenao Zhang , Zhihan Liu , Boyi Liu , Yufeng Zhang , Yingxiang Yang , Yongfei Liu , Liyu Chen , Tao Sun , Zhaoran Wang

Large Language Models (LLMs) are increasingly used as proxies for human subjects in social science surveys, but their reliability and susceptibility to known human-like response biases, such as central tendency, opinion floating and primacy…

Computation and Language · Computer Science 2025-10-17 Jens Rupprecht , Georg Ahnert , Markus Strohmaier

Ensuring that large language models (LLMs) are both helpful and harmless is a critical challenge, as overly strict constraints can lead to excessive refusals, while permissive models risk generating harmful content. Existing approaches,…

In this paper, we investigate the phenomena of "selection biases" in Large Language Models (LLMs), focusing on problems where models are tasked with choosing the optimal option from an ordered sequence. We delve into biases related to…

Computation and Language · Computer Science 2024-06-06 Sheng-Lun Wei , Cheng-Kuang Wu , Hen-Hsen Huang , Hsin-Hsi Chen

As large language models (LLMs) gain popularity, their vulnerability to adversarial attacks emerges as a primary concern. While fine-tuning models on domain-specific datasets is often employed to improve model performance, it can…

Computation and Language · Computer Science 2026-02-24 Punya Syon Pandey , Samuel Simko , Kellin Pelrine , Zhijing Jin