English
Related papers

Related papers: ELSPR: Evaluator LLM Training Data Self-Purificati…

200 papers

A common technique for aligning large language models (LLMs) relies on acquiring human preferences by comparing multiple generations conditioned on a fixed context. This method, however, relies solely on pairwise comparisons, where the…

Computation and Language · Computer Science 2025-01-09 Hritik Bansal , Ashima Suvarna , Gantavya Bhatt , Nanyun Peng , Kai-Wei Chang , Aditya Grover

Large language models (LLMs) have achieved remarkable success, yet aligning their generations with human preferences remains a critical challenge. Existing approaches to preference modeling often rely on an explicit or implicit reward…

Computation and Language · Computer Science 2025-05-09 Zhuocheng Gong , Jian Guan , Wei Wu , Huishuai Zhang , Dongyan Zhao

Recent advances have made long-form report-generating systems widely available. This has prompted evaluation frameworks that use LLM-as-judge protocols and claim verification, along with meta-evaluation frameworks that seek to validate…

Test-time alignment methods offer a promising alternative to fine-tuning by steering the outputs of large language models (LLMs) at inference time with lightweight interventions on their internal representations. Recently, a prominent and…

Computation and Language · Computer Science 2026-04-28 Imranul Ashrafi , Inigo Jauregi Unanue , Massimo Piccardi

The exponential increase in scientific literature and online information necessitates efficient methods for extracting knowledge from textual data. Natural language processing (NLP) plays a crucial role in addressing this challenge,…

Computation and Language · Computer Science 2025-10-22 Zhyar Rzgar K. Rostam , Gábor Kertész

Understanding human preferences is crucial for improving foundation models and building personalized AI systems. However, preferences are inherently diverse and complex, making it difficult for traditional reward models to capture their…

Artificial Intelligence · Computer Science 2025-06-12 Feng Luo , Rui Yang , Hao Sun , Chunyuan Deng , Jiarui Yao , Jingyan Shen , Huan Zhang , Hanjie Chen

While large language models show promise in mental healthcare, evaluating their therapeutic competence remains challenging due to the unstructured and longitudinal nature of counseling. We argue that current evaluation paradigms suffer from…

Computation and Language · Computer Science 2026-01-29 Zhuang Chen , Dazhen Wan , Zhangkai Zheng , Guanqun Bi , Xiyao Xiao , Binghang Li , Minlie Huang

Human preference judgments are pivotal in guiding large language models (LLMs) to produce outputs that align with human values. Human evaluations are also used in summarization tasks to compare outputs from various systems, complementing…

Computation and Language · Computer Science 2023-10-31 Yebowen Hu , Kaiqiang Song , Sangwoo Cho , Xiaoyang Wang , Hassan Foroosh , Fei Liu

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

Recently, tremendous strides have been made to align the generation of Large Language Models (LLMs) with human values to mitigate toxic or unhelpful content. Leveraging Reinforcement Learning from Human Feedback (RLHF) proves effective and…

Computation and Language · Computer Science 2024-06-05 Mingye Zhu , Yi Liu , Lei Zhang , Junbo Guo , Zhendong Mao

Aligning Large Language Model (LLM) responses with human preferences is vital for building safe and controllable AI systems. While preference optimization methods based on Plackett-Luce (PL) and Bradley-Terry (BT) models have shown promise,…

Artificial Intelligence · Computer Science 2026-03-23 Xiandong Zou , Wanyu Lin , Yuchen Li , Pan Zhou

Automated negotiation in complex, multi-party and multi-issue settings critically depends on accurate opponent modeling. However, conventional numerical-only approaches fail to capture the qualitative information embedded in natural…

Pairwise comparison methods, such as Fuzzy Preference Relations and Saaty's Multiplicative Preference Relations, are widely used to model expert judgments in multi-criteria decision-making. However, their application is limited by the high…

Artificial Intelligence · Computer Science 2025-10-10 Diego García-Zamora , Álvaro Labella , José Rui Figueira

Conversational Recommender Systems (CRSs) have emerged as a transformative paradigm for offering personalized recommendations through natural language dialogue. However, they face challenges with knowledge sparsity, as users often provide…

Computation and Language · Computer Science 2025-03-11 Zhangchi Qiu , Linhao Luo , Zicheng Zhao , Shirui Pan , Alan Wee-Chung Liew

Ranking documents using Large Language Models (LLMs) by directly feeding the query and candidate documents into the prompt is an interesting and practical problem. However, researchers have found it difficult to outperform fine-tuned…

Information Retrieval · Computer Science 2024-03-29 Zhen Qin , Rolf Jagerman , Kai Hui , Honglei Zhuang , Junru Wu , Le Yan , Jiaming Shen , Tianqi Liu , Jialu Liu , Donald Metzler , Xuanhui Wang , Michael Bendersky

Language model (LM) post-training relies on two stages of human supervision: task demonstrations for supervised finetuning (SFT), followed by preference comparisons for reinforcement learning from human feedback (RLHF). As LMs become more…

Machine Learning · Computer Science 2025-01-15 Yaowen Ye , Cassidy Laidlaw , Jacob Steinhardt

Existing tool-learning methods usually rely on supervised fine-tuning, they often overlook fine-grained optimization of internal tool call details, leading to limitations in preference alignment and error discrimination. To overcome these…

Computation and Language · Computer Science 2025-05-27 Chengrui Huang , Shen Gao , Zhengliang Shi , Dongsheng Wang , Shuo Shang

Reinforcement learning (RL) is a key paradigm for post-training large language models (LLMs), but the widely used Group Relative Policy Optimization (GRPO) often suffers from entropy collapse: exploration quickly disappears, policies…

Machine Learning · Computer Science 2026-05-19 Chen Wang , Zhaochun Li , Jionghao Bai , Hexuan Deng , Ge Lan , Yue Wang

Multileaved comparison methods generalize interleaved comparison methods to provide a scalable approach for comparing ranking systems based on regular user interactions. Such methods enable the increasingly rapid research and development of…

Information Retrieval · Computer Science 2017-11-28 Harrie Oosterhuis , Maarten de Rijke

Process rewards have been widely used in deep reinforcement learning to improve training efficiency, reduce variance, and prevent reward hacking. In LLM reasoning, existing works also explore various solutions for learning effective process…

Machine Learning · Computer Science 2026-05-21 Xian Wu , Kaijie Zhu , Ying Zhang , Lun Wang , Wenbo Guo
‹ Prev 1 8 9 10 Next ›