English
Related papers

Related papers: Automatic Pair Construction for Contrastive Post-t…

200 papers

Automated program repair (APR) attempts to reduce manual debugging efforts and plays a vital role in software maintenance. Despite remarkable progress, APR is still limited in generating overfitting patches, i.e., patches passing available…

Software Engineering · Computer Science 2026-04-07 Quanjun Zhang , Ye Shang , Haichuan Hu , Chunrong Fang , Zhenyu Chen , Liang Xiao

Previous research has sought to enhance the graph reasoning capabilities of LLMs by supervised fine-tuning on synthetic graph data. While these led to specialized LLMs better at solving graph algorithm problems, we don't need LLMs for…

Machine Learning · Computer Science 2025-08-19 Yizhuo Zhang , Heng Wang , Shangbin Feng , Zhaoxuan Tan , Xinyun Liu , Yulia Tsvetkov

Multi-preference optimization enriches language-model alignment beyond pairwise preferences by contrasting entire sets of helpful and undesired responses, thereby enabling richer training signals for large language models. During self-play…

Machine Learning · Computer Science 2025-06-10 Taneesh Gupta , Rahul Madhavan , Xuchao Zhang , Chetan Bansal , Saravan Rajmohan

Finding preferences expressed in natural language is an important but challenging task. State-of-the-art(SotA) methods leverage transformer-based models such as BERT, RoBERTa, etc. and graph neural architectures such as graph attention…

Computation and Language · Computer Science 2023-10-13 Inwon Kang , Sikai Ruan , Tyler Ho , Jui-Chien Lin , Farhad Mohsin , Oshani Seneviratne , Lirong Xia

Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much…

Computer Vision and Pattern Recognition · Computer Science 2022-08-01 Tejas Srinivasan , Xiang Ren , Jesse Thomason

Although Large Language Models (LLMs) have made remarkable progress, current preference optimization methods still struggle to align directional consistency while preserving reasoning diversity. To address this limitation, we propose…

Computation and Language · Computer Science 2026-05-12 Mengyi Deng , Zhiwei Li , Xin Li , Tingyu Zhu , Yulan Yuan , Zhijiang Guo , Wei Wang

The alignment of large language models (LLMs) with human preferences remains a key challenge. While post-training techniques like Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization (DPO) have achieved…

Artificial Intelligence · Computer Science 2025-07-11 Qingyu Yin , Chak Tou Leong , Minjun Zhu , Hanqi Yan , Qiang Zhang , Yulan He , Wenjie Li , Jun Wang , Yue Zhang , Linyi Yang

Long-form generation is crucial for academic writing papers and repo-level code generation. Despite this, current models, including GPT-4o, still exhibit unsatisfactory performance. Existing methods that utilize preference learning with…

Computation and Language · Computer Science 2025-05-21 Bowen Ping , Jiali Zeng , Fandong Meng , Shuo Wang , Jie Zhou , Shanghang Zhang

Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignment, they all rely on a more advanced model, especially…

Computation and Language · Computer Science 2025-06-02 Hui Huang , Jiaheng Liu , Yancheng He , Shilong Li , Bing Xu , Conghui Zhu , Muyun Yang , Tiejun Zhao

DPO (Direct Preference Optimization) has become a widely used offline preference optimization algorithm due to its simplicity and training stability. However, DPO is prone to overfitting and collapse. To address these challenges, we propose…

Machine Learning · Computer Science 2025-08-26 Rui Wang , Qianguo Sun , Chao Song , Junlong Wu , Tianrong Chen , Zhiyun Zeng , Yu Li

Reliable AI systems require large language models (LLMs) to exhibit behaviors aligned with human preferences and values. However, most existing alignment approaches operate at training time and rely on additional high-quality data,…

Artificial Intelligence · Computer Science 2026-02-25 Baolong Bi , Yuyao Ge , Shenghua Liu , Yuchen He , Siqian Tong , Lizhe Chen , Lingrui Mei , Zehao Li , Yiwei Wang , Yujun Cai , Ming-Hsuan Yang , Xueqi Cheng

Existing studies on preference optimization (PO) have centered on constructing pairwise preference data following simple heuristics, such as maximizing the margin between preferred and dispreferred completions based on human (or AI) ranked…

Artificial Intelligence · Computer Science 2025-02-10 Zhuotong Chen , Fang Liu , Xuan Zhu , Yanjun Qi , Mohammad Ghavamzadeh

Aligning Large Language Models (LLMs) with human preferences is crucial in ensuring desirable and controllable model behaviors. Current methods, such as Reinforcement Learning from Human Feedback (RLHF) and Direct Preference Optimization…

Computation and Language · Computer Science 2025-10-24 Yang Zhao , Yixin Wang , Mingzhang Yin

Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…

Computation and Language · Computer Science 2025-06-16 Víctor Gallego

Language models are aligned to emulate the collective voice of many, resulting in outputs that align with no one in particular. Steering LLMs away from generic output is possible through supervised finetuning or RLHF, but requires…

Computation and Language · Computer Science 2025-04-22 Omar Shaikh , Michelle S. Lam , Joey Hejna , Yijia Shao , Hyundong Cho , Michael S. Bernstein , Diyi Yang

Direct Preference Optimization (DPO) has emerged as a simple and effective approach for aligning large language models (LLMs) with human preferences, bypassing the need for a learned reward model. Despite its growing adoption, a fundamental…

Machine Learning · Computer Science 2025-11-10 Yu Pan , Zhongze Cai , Guanting Chen , Huaiyang Zhong , Chonghuan Wang

Translation is important for cross-language communication, and many efforts have been made to improve its accuracy. However, less investment is conducted in aligning translations with human preferences, such as translation tones or styles.…

Computation and Language · Computer Science 2024-10-16 Shuqiao Sun , Yutong Yao , Peiwen Wu , Feijun Jiang , Kaifu Zhang

Large language models (LLMs) have revolutionized the role of AI, yet pose potential social risks. To steer LLMs towards human preference, alignment technologies have been introduced and gained increasing attention. Nevertheless, existing…

Computation and Language · Computer Science 2024-10-01 Shitong Duan , Xiaoyuan Yi , Peng Zhang , Yan Liu , Zheng Liu , Tun Lu , Xing Xie , Ning Gu

Data-to-Text Generation (D2T), a classic natural language generation problem, aims at producing fluent descriptions for structured input data, such as a table. Existing D2T works mainly focus on describing the superficial associative…

Computation and Language · Computer Science 2024-08-16 Yuhao Dan , Junfeng Tian , Jie Zhou , Ming Yan , Ji Zhang , Qin Chen , Liang He

Contrastive self-supervised learning has become a prominent technique in representation learning. The main step in these methods is to contrast semantically similar and dissimilar pairs of samples. However, in the domain of Natural Language…

Computation and Language · Computer Science 2022-06-07 Amrita Bhattacharjee , Mansooreh Karami , Huan Liu