English
Related papers

Related papers: ProDS: Preference-oriented Data Selection for Inst…

200 papers

Recommender systems aim to predict personalized rankings based on user preference data. With the rise of Language Models (LMs), LM-based recommenders have been widely explored due to their extensive world knowledge and powerful reasoning…

Information Retrieval · Computer Science 2024-11-08 Yuxin Chen , Junfei Tan , An Zhang , Zhengyi Yang , Leheng Sheng , Enzhi Zhang , Xiang Wang , Tat-Seng Chua

Iterative data generation and model re-training can effectively align large language models(LLMs) to human preferences. The process of data sampling is crucial, as it significantly influences the success of policy improvement. Repeated…

Computation and Language · Computer Science 2024-10-07 Hai Ye , Hwee Tou Ng

Direct Preference Optimization (DPO) has become a standard framework for safety alignment, but its reliance on pairwise preference updates makes training sensitive to imperfect supervision. Existing robust DPO methods often address this…

Machine Learning · Computer Science 2026-05-27 Jilong Liu , Yonghui Yang , Pengyang Shao , Wenjian Tao , Hao Zhan , Haokai Ma , Wei Qin , Richang Hong

Instruction tuning has been central to the success of recent vision-language models (VLMs), but it remains expensive-requiring large-scale datasets, high-quality annotations, and large compute budgets. We propose PRioritized cOncept…

Computer Vision and Pattern Recognition · Computer Science 2026-02-26 Shivam Chandhok , Qian Yang , Oscar Manas , Kanishk Jain , Leonid Sigal , Aishwarya Agrawal

Alignment, endowing a pre-trained Large language model (LLM) with the ability to follow instructions, is crucial for its real-world applications. Conventional supervised fine-tuning (SFT) methods formalize it as causal language modeling…

Computation and Language · Computer Science 2024-12-18 Yuchen Fan , Yuzhong Hong , Qiushi Wang , Junwei Bao , Hongfei Jiang , Yang Song

Direct Preference Optimization (DPO) has been proposed as an effective and efficient alternative to reinforcement learning from human feedback (RLHF). In this paper, we propose a novel and enhanced version of DPO based on curriculum…

Computer Vision and Pattern Recognition · Computer Science 2025-05-12 Florinel-Alin Croitoru , Vlad Hondru , Radu Tudor Ionescu , Nicu Sebe , Mubarak Shah

In the domain of complex reasoning tasks, such as mathematical reasoning, recent advancements have proposed the use of Direct Preference Optimization (DPO) to suppress output of dispreferred responses, thereby enhancing the long-chain…

Computation and Language · Computer Science 2025-10-27 Weibin Liao , Xu Chu , Yasha Wang

The ultimate goal of multi-objective optimisation is to help a decision maker (DM) identify solution(s) of interest (SOI) achieving satisfactory trade-offs among multiple conflicting criteria. This can be realised by leveraging DM's…

Neural and Evolutionary Computing · Computer Science 2019-10-01 Ke Li , Minhui Liao , Kalyanmoy Deb , Geyong Min , Xin Yao

A reliable and comprehensive evaluation metric that aligns with manual preference assessments is crucial for conversational head video synthesis methods development. Existing quantitative evaluations often fail to capture the full…

Computer Vision and Pattern Recognition · Computer Science 2023-08-03 Mohan Zhou , Yalong Bai , Wei Zhang , Ting Yao , Tiejun Zhao , Tao Mei

Finetuning large language models on instruction data is crucial for enhancing pre-trained knowledge and improving instruction-following capabilities. As instruction datasets proliferate, selecting optimal data for effective training becomes…

Computation and Language · Computer Science 2024-09-18 Simon Yu , Liangyu Chen , Sara Ahmadian , Marzieh Fadaee

Selective Prediction is the task of rejecting inputs a model would predict incorrectly on. This involves a trade-off between input space coverage (how many data points are accepted) and model utility (how good is the performance on accepted…

Human preference data is essential for aligning large language models (LLMs) with human values, but collecting such data is often costly and inefficient-motivating the need for efficient data selection methods that reduce annotation costs…

Computation and Language · Computer Science 2026-04-21 Seohyeong Lee , Eunwon Kim , Hwaran Lee , Buru Chang

Recent alignment algorithms such as direct preference optimization (DPO) have been developed to improve the safety of large language models (LLMs) by training these models to match human behaviors exemplified by preference data. However,…

Computation and Language · Computer Science 2025-03-04 Rheeya Uppaal , Apratim Dey , Yiting He , Yiqiao Zhong , Junjie Hu

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…

Computer Vision and Pattern Recognition · Computer Science 2024-12-19 Runtao Liu , Haoyu Wu , Zheng Ziqiang , Chen Wei , Yingqing He , Renjie Pi , Qifeng Chen

Modern alignment pipelines are increasingly replacing expensive human preference labels with evaluations from large language models (LLM-as-Judge). However, AI labels can be systematically biased compared to high-quality human feedback…

Machine Learning · Statistics 2026-02-10 Xintao Xia , Zhiqiu Xia , Linjun Zhang , Zhanrui Cai

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

Computation and Language · Computer Science 2025-07-29 Hyeonji Lee , Daejin Jo , Seohwan Yun , Sungwoong Kim

Recent advancements in large language model alignment leverage token-level supervisions to perform fine-grained preference optimization. However, existing token-level alignment methods either optimize on all available tokens, which can be…

Computation and Language · Computer Science 2025-11-07 Kailai Yang , Zhiwei Liu , Qianqian Xie , Jimin Huang , Erxue Min , Sophia Ananiadou

We aim to select data subsets for the fine-tuning of large language models to more effectively follow instructions. Prior work has emphasized the importance of diversity in dataset curation but relied on heuristics such as the number of…

Machine Learning · Computer Science 2024-02-07 Peiqi Wang , Yikang Shen , Zhen Guo , Matthew Stallone , Yoon Kim , Polina Golland , Rameswar Panda

For Time-Domain Global Similarity (TDGS) method, which transforms the data cleaning problem into a binary classification problem about the physical similarity between channels, directly adopting common performance measures could only…

Machine Learning · Computer Science 2018-01-17 Ting Lan , Jian Liu , Hong Qin

End-to-end autonomous driving has substantially progressed by directly predicting future trajectories from raw perception inputs, which bypasses traditional modular pipelines. However, mainstream methods trained via imitation learning…

Robotics · Computer Science 2025-09-23 Shuyao Shang , Yuntao Chen , Yuqi Wang , Yingyan Li , Zhaoxiang Zhang