English
Related papers

Related papers: Aligning Deep Implicit Preferences by Learning to …

200 papers

Large language models (LLMs) have shown remarkable success, but aligning them with human preferences remains a core challenge. As individuals have their own, multi-dimensional preferences, recent studies have explored multi-dimensional…

Machine Learning · Computer Science 2025-06-03 Minhyeon Oh , Seungjoon Lee , Jungseul Ok

While Large Language Models (LLMs) demonstrate exceptional performance in surface-level text generation, their nature in handling complex multi-step reasoning tasks often remains one of ``statistical fitting'' rather than systematic logical…

Machine Learning · Computer Science 2026-01-27 Lianlei Shan , Han Chen , Yixuan Wang , Zhenjie Liu , Wei Li

Alignment algorithms are widely used to align large language models (LLMs) to human users based on preference annotations. Typically these (often divergent) preferences are aggregated over a diverse set of users, resulting in fine-tuned…

Computation and Language · Computer Science 2025-05-21 Cristina Garbacea , Chenhao Tan

Actively inferring user preferences, for example by asking good questions, is important for any human-facing decision-making system. Active inference allows such systems to adapt and personalize themselves to nuanced individual preferences.…

Computation and Language · Computer Science 2024-06-27 Wasu Top Piriyakulkij , Volodymyr Kuleshov , Kevin Ellis

LLM unlearning is essential for mitigating safety, copyright, and privacy concerns in pre-trained large language models (LLMs). Compared to preference alignment, it offers a more explicit way by removing undesirable knowledge characterized…

Machine Learning · Computer Science 2026-03-12 Junfeng Liao , Qizhou Wang , Shanshan Ye , Xin Yu , Ling Chen , Zhen Fang

Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories, rather than explicit reward signals. While PbRL has demonstrated…

Machine Learning · Computer Science 2024-04-18 Wenhao Zhan , Masatoshi Uehara , Wen Sun , Jason D. Lee

Evaluation and alignment pipelines for large language models increasingly rely on LLM-based judges, whose behavior is guided by natural-language rubrics and validated on benchmarks. We identify a previously under-recognized vulnerability in…

Cryptography and Security · Computer Science 2026-02-17 Ruomeng Ding , Yifei Pang , He Sun , Yizhong Wang , Zhiwei Steven Wu , Zhun Deng

In reinforcement learning from human feedback, preference-based reward models play a central role in aligning large language models to human-aligned behavior. However, recent studies show that these models are prone to reward hacking and…

Artificial Intelligence · Computer Science 2025-10-23 Wenqian Ye , Guangtao Zheng , Aidong Zhang

Applying large language models (LLMs) to assist in psycho-counseling is an emerging and meaningful approach, driven by the significant gap between patient needs and the availability of mental health support. However, current LLMs struggle…

Computation and Language · Computer Science 2026-04-14 Mian Zhang , Shaun M. Eack , Zhiyu Zoey Chen

Achieving both accuracy and diverse reasoning remains challenging for Large Language Models (LLMs) in complex domains like mathematics. A key bottleneck is evaluating intermediate reasoning steps to guide generation without costly human…

Machine Learning · Computer Science 2025-10-14 Adam Younsi , Ahmed Attia , Abdalgader Abubaker , Mohamed El Amine Seddik , Hakim Hacid , Salem Lahlou

Preference mechanisms, such as human preference, LLM-as-a-Judge (LaaJ), and reward models, are central to aligning and evaluating large language models (LLMs). Yet, the underlying concepts that drive these preferences remain poorly…

Computation and Language · Computer Science 2025-05-30 Nitay Calderon , Liat Ein-Dor , Roi Reichart

Recommender systems are critical for delivering personalized content across digital platforms, and recent advances in Large Language Models (LLMs) offer new opportunities to enhance them with richer world knowledge and explicit reasoning…

Information Retrieval · Computer Science 2026-05-22 Jingtong Gao , Zeyu Song , Chi Lu , Xiaopeng Li , Derong Xu , Maolin Wang , Peng Jiang , Kun Gai , Qingpeng Cai , Xiangyu Zhao

Large language models (LLMs) face a fundamental trade-off between computational efficiency (e.g., number of parameters) and output quality, especially when deployed on computationally limited devices such as phones or laptops. One way to…

Recent research has increasingly focused on evaluating large language models' (LLMs) alignment with diverse human values and preferences, particularly for open-ended tasks like story generation. Traditional evaluation metrics rely heavily…

Computation and Language · Computer Science 2024-10-07 Danqing Wang , Kevin Yang , Hanlin Zhu , Xiaomeng Yang , Andrew Cohen , Lei Li , Yuandong Tian

Clinical decision support requires not only correct answers but also clinically valid reasoning. We propose Differential Reasoning Learning (DRL), a framework that improves clinical agents by learning from reasoning discrepancies. From…

Artificial Intelligence · Computer Science 2026-02-11 Jinsong Liu , Yuhang Jiang , Ramayya Krishnan , Rema Padman , Yiye Zhang , Jiang Bian

Driven by advances in Large Language Models (LLMs), integrating them into recommendation tasks has gained interest due to their strong semantic understanding and prompt flexibility. Prior work encoded user-item interactions or metadata into…

Information Retrieval · Computer Science 2025-06-10 Keyu Zhao , Fengli Xu , Yong Li

Despite great recent advances achieved by deep neural networks (DNNs), they are often vulnerable to adversarial attacks. Intensive research efforts have been made to improve the robustness of DNNs; however, most empirical defenses can be…

Machine Learning · Computer Science 2023-01-02 Jiawei Zhang , Linyi Li , Ce Zhang , Bo Li

We propose cognitive prompting as a novel approach to guide problem-solving in large language models (LLMs) through structured, human-like cognitive operations, such as goal clarification, decomposition, filtering, abstraction, and pattern…

Computation and Language · Computer Science 2024-12-03 Oliver Kramer , Jill Baumann

Effective prompting of generative AI is challenging for many users, particularly in expressing context for comprehension tasks such as explaining spreadsheet formulas, Python code, and text passages. Prompt middleware aims to address this…

Human-Computer Interaction · Computer Science 2024-12-04 Ian Drosos , Jack Williams , Advait Sarkar , Nicholas Wilson

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Machine Learning · Computer Science 2021-12-22 Tom Bewley , Freddy Lecue