English
Related papers

Related papers: BPL: Bias-adaptive Preference Distillation Learnin…

200 papers

Learning contrastive representations from pairwise comparisons has achieved remarkable success in various fields, such as natural language processing, computer vision, and information retrieval. Collaborative filtering algorithms based on…

Information Retrieval · Computer Science 2023-08-01 Bin Liu , Qin Luo , Bang Wang

Alignment techniques enable Large Language Models (LLMs) to generate outputs that align with human preferences and play a crucial role in their effectiveness. However, their impact often diminishes when applied to Small Language Models…

Computation and Language · Computer Science 2025-03-06 Shiping Gao , Fanqi Wan , Jiajian Guo , Xiaojun Quan , Qifan Wang

This paper proposes a new approach to training recommender systems called deviation-based learning. The recommender and rational users have different knowledge. The recommender learns user knowledge by observing what action users take upon…

Theoretical Economics · Economics 2022-08-22 Junpei Komiyama , Shunya Noda

The increasing scale of general-purpose Pre-trained Language Models (PLMs) necessitates the study of more efficient adaptation across different downstream tasks. In this paper, we establish a Black-box Discrete Prompt Learning (BDPL) to…

Computation and Language · Computer Science 2023-02-24 Shizhe Diao , Zhichao Huang , Ruijia Xu , Xuechun Li , Yong Lin , Xiao Zhou , Tong Zhang

Preference-Based reinforcement learning (PBRL) learns directly from the preferences of human teachers regarding agent behaviors without needing meticulously designed reward functions. However, existing PBRL methods often learn primarily…

Machine Learning · Computer Science 2024-10-16 Ziang Liu , Junjie Xu , Xingjiao Wu , Jing Yang , Liang He

We propose Reinforcement Learning from Contrastive Distillation (RLCD), a method for aligning language models to follow principles expressed in natural language (e.g., to be more harmless) without using human feedback. RLCD creates…

Computation and Language · Computer Science 2024-03-19 Kevin Yang , Dan Klein , Asli Celikyilmaz , Nanyun Peng , Yuandong Tian

A popular approach to model compression is to train an inexpensive student model to mimic the class probabilities of a highly accurate but cumbersome teacher model. Surprisingly, this two-step knowledge distillation process often leads to…

Machine Learning · Statistics 2021-04-21 Tri Dao , Govinda M Kamath , Vasilis Syrgkanis , Lester Mackey

Large language models have recently enabled a generative paradigm for query expansion, but their high inference cost makes direct deployment difficult in practical retrieval systems. To address this issue, a retrieval-feedback-driven…

Information Retrieval · Computer Science 2026-03-17 Minghan Li , Guodong Zhou

Aligning small language models (SLMs) with human values typically involves distilling preference knowledge from large language models (LLMs). However, existing distillation methods model preference knowledge in teacher LLMs by comparing…

Computation and Language · Computer Science 2025-02-21 Yanggan Gu , Junzhuo Li , Sirui Huang , Xin Zou , Zhenghua Li , Xuming Hu

We present DistillFlow, a knowledge distillation approach to learning optical flow. DistillFlow trains multiple teacher models and a student model, where challenging transformations are applied to the input of the student model to generate…

Computer Vision and Pattern Recognition · Computer Science 2021-06-09 Pengpeng Liu , Michael R. Lyu , Irwin King , Jia Xu

Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model counterparts, exacerbated…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Geon Yeong Park , Sang Wan Lee , Jong Chul Ye

Feature-based knowledge distillation has been applied to compress modern recommendation models, usually with projectors that align student (small) recommendation models' dimensions with teacher dimensions. However, existing studies have…

Information Retrieval · Computer Science 2025-01-14 Zhangchi Zhu , Wei Zhang

Knowledge distillation is widely used as a means of improving the performance of a relatively simple student model using the predictions from a complex teacher model. Several works have shown that distillation significantly boosts the…

Machine Learning · Computer Science 2021-07-09 Michal Lukasik , Srinadh Bhojanapalli , Aditya Krishna Menon , Sanjiv Kumar

Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction. However, the observed feedback usually suffer…

Information Retrieval · Computer Science 2024-02-09 Jun Wang , Haoxuan Li , Chi Zhang , Dongxu Liang , Enyun Yu , Wenwu Ou , Wenjia Wang

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to…

Computation and Language · Computer Science 2023-12-25 Jiahao Xu , Wei Shao , Lihui Chen , Lemao Liu

Debiased recommender models have recently attracted increasing attention from the academic and industry communities. Existing models are mostly based on the technique of inverse propensity score (IPS). However, in the recommendation domain,…

Information Retrieval · Computer Science 2022-08-16 Quanyu Dai , Zhenhua Dong , Xu Chen

Successful continual learning of new knowledge would enable intelligent systems to recognize more and more classes of objects. However, current intelligent systems often fail to correctly recognize previously learned classes of objects when…

Computer Vision and Pattern Recognition · Computer Science 2021-08-21 Changhong Zhong , Zhiying Cui , Ruixuan Wang , Wei-Shi Zheng

Distillation is the technique of training a "student" model based on examples that are labeled by a separate "teacher" model, which itself is trained on a labeled dataset. The most common explanations for why distillation "works" are…

Knowledge distillation is considered as a training and compression strategy in which two neural networks, namely a teacher and a student, are coupled together during training. The teacher network is supposed to be a trustworthy predictor…

Computation and Language · Computer Science 2020-12-29 Peyman Passban , Yimeng Wu , Mehdi Rezagholizadeh , Qun Liu

Semi-supervised learning by self-training heavily relies on pseudo-label selection (PLS). The selection often depends on the initial model fit on labeled data. Early overfitting might thus be propagated to the final model by selecting…

Machine Learning · Statistics 2023-06-27 Julian Rodemann , Jann Goschenhofer , Emilio Dorigatti , Thomas Nagler , Thomas Augustin