English
Related papers

Related papers: Chain of Alignment: Integrating Public Will with E…

200 papers

Value alignment is central to the development of safe and socially compatible artificial intelligence. However, how Large Language Models (LLMs) represent and enact human values in real-world decision contexts remains under-explored. We…

Computation and Language · Computer Science 2026-01-14 Jen-tse Huang , Jiantong Qin , Xueli Qiu , Sharon Levy , Michelle R. Kaufman , Mark Dredze

Retrieval-augmented generation (RAG) with large language models (LLMs) is especially valuable in specialized domains, where precision is critical. To more specialize the LLMs into a target domain, domain-specific RAG has recently been…

Computation and Language · Computer Science 2025-02-24 Juntae Lee , Jihwan Bang , Seunghan Yang , Kyuhong Shim , Simyung Chang

Language models (LMs) are increasingly used as simulacra for people, yet their ability to match the distribution of views of a specific demographic group and be \textit{distributionally aligned} remains uncertain. This notion of…

Computation and Language · Computer Science 2024-11-11 Nicole Meister , Carlos Guestrin , Tatsunori Hashimoto

Large language models (LLMs) exhibit cultural bias from overrepresented viewpoints in training data, yet cultural alignment remains a challenge due to limited cultural knowledge and a lack of exploration into effective learning approaches.…

Computation and Language · Computer Science 2025-12-16 Chunhua Liu , Kabir Manandhar Shrestha , Sukai Huang

Reward models (RMs) play a crucial role in Reinforcement Learning from Human Feedback by serving as proxies for human preferences in aligning large language models. However, they suffer from various biases which could lead to reward…

Artificial Intelligence · Computer Science 2026-03-18 Xiao Zhu , Chenmien Tan , Pinzhen Chen , Rico Sennrich , Huiming Wang , Yanlin Zhang , Hanxu Hu

Alignment of large language models (LLMs) with principles like helpfulness, honesty, and harmlessness typically relies on scalar rewards that obscure which objectives drive the training signal. We introduce QA-LIGN, which decomposes…

Computation and Language · Computer Science 2025-12-05 Jacob Dineen , Aswin RRV , Qin Liu , Zhikun Xu , Xiao Ye , Ming Shen , Zhaonan Li , Shijie Lu , Chitta Baral , Muhao Chen , Ben Zhou

Policy compliance assessment is a fundamental task of evaluating whether an input case strictly complies with a set of human-defined rules, more generally known as policies. In practice, human experts follow a systematic, step-by-step…

Computation and Language · Computer Science 2025-09-30 Joseph Marvin Imperial , Harish Tayyar Madabushi

Large Language Models (LLMs) are typically aligned with human values using preference data or predefined principles such as helpfulness, honesty, and harmlessness. However, as AI systems progress toward Artificial General Intelligence (AGI)…

Computation and Language · Computer Science 2025-12-08 Panatchakorn Anantaprayoon , Nataliia Babina , Jad Tarifi , Nima Asgharbeygi

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single optimizeable objective. We seek to answer what it would take to simultaneously align a model…

Machine Learning · Computer Science 2025-10-02 Yiran Shen , Yu Xia , Jonathan Chang , Prithviraj Ammanabrolu

There is growing consensus that language model (LM) developers should not be the sole deciders of LM behavior, creating a need for methods that enable the broader public to collectively shape the behavior of LM systems that affect them. To…

Artificial Intelligence · Computer Science 2024-06-13 Saffron Huang , Divya Siddarth , Liane Lovitt , Thomas I. Liao , Esin Durmus , Alex Tamkin , Deep Ganguli

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Artificial Intelligence · Computer Science 2026-04-29 Peiming Li , Zhiyuan Hu , Yang Tang , Shiyu Li , Xi Chen

Recent advances in Large Language Models (LLMs) highlight the need to align their behaviors with human values. A critical, yet understudied, issue is the potential divergence between an LLM's stated preferences (its reported alignment with…

Artificial Intelligence · Computer Science 2025-06-03 Zhuojun Gu , Quan Wang , Shuchu Han

We present an ethical decision-making framework that refines a pre-trained reinforcement learning (RL) model using a task-agnostic ethical layer. Following initial training, the RL model undergoes ethical fine-tuning, where human feedback…

Computers and Society · Computer Science 2026-05-05 Rohit K. Dubey , Damian Dailisan , Sachit Mahajan

Social alignment in AI systems aims to ensure that these models behave according to established societal values. However, unlike humans, who derive consensus on value judgments through social interaction, current language models (LMs) are…

Computation and Language · Computer Science 2023-10-31 Ruibo Liu , Ruixin Yang , Chenyan Jia , Ge Zhang , Denny Zhou , Andrew M. Dai , Diyi Yang , Soroush Vosoughi

Natural language interaction with agentic Artificial Intelligence (AI), driven by Large Language Models (LLMs), is expected to remain a dominant paradigm in the near future. While humans instinctively align their communication with mental…

Computation and Language · Computer Science 2025-05-21 Mehdi Jafari , Devin Yuncheng Hua , Hao Xue , Flora Salim

While recent advancements in aligning Large Language Models (LLMs) with recommendation tasks have shown great potential and promising performance overall, these aligned recommendation LLMs still face challenges in complex scenarios. This is…

Information Retrieval · Computer Science 2025-02-18 Yi Fang , Wenjie Wang , Yang Zhang , Fengbin Zhu , Qifan Wang , Fuli Feng , Xiangnan He

Reward Models, essential for guiding Large Language Model optimization, are typically trained on fixed preference datasets, resulting in rigid alignment to single, implicit preference distributions. This prevents adaptation to diverse…

Computation and Language · Computer Science 2025-07-08 Zhuohao Yu , Jiali Zeng , Weizheng Gu , Yidong Wang , Jindong Wang , Fandong Meng , Jie Zhou , Yue Zhang , Shikun Zhang , Wei Ye

Large language models (LLMs) are increasingly being used for tasks where outputs shape human decisions, so it is critical to verify that their responses consistently reflect desired human values. Humans, as individuals or groups, don't…

Artificial Intelligence · Computer Science 2026-01-16 Aman Gupta , Denny O'Shea , Fazl Barez

Language models trained via outcome-based reinforcement learning (RL) to reason using chain-of-thought (CoT) have shown remarkable performance. Monitoring such a model's CoT may allow us to understand its intentions and detect potential…

Machine Learning · Computer Science 2025-11-03 Arun Jose

Large language models (LLMs) are increasingly being used as decision aids. However, users have diverse values and preferences that can affect their decision-making, which requires novel methods for LLM alignment and personalization.…

Computation and Language · Computer Science 2025-07-15 Bharadwaj Ravichandran , David Joy , Paul Elliott , Brian Hu , Jadie Adams , Christopher Funk , Emily Veenhuis , Anthony Hoogs , Arslan Basharat