English
Related papers

Related papers: RLCD: Reinforcement Learning from Contrastive Dist…

200 papers

Enabling Large Language Models (LLMs) to continuously improve from environmental interactions is a central challenge in post-training. While on-policy self-distillation offers a promising paradigm, existing methods predominantly treat…

Machine Learning · Computer Science 2026-05-14 Yuwei Zhang , Sha Li , Changlong Yu , Qin Lu , Shuowei Jin , Chengyu Dong , Haoran Liu , Ilgee Hong , Xintong Li , Zhenyu Shi , Bing Yin , Jingbo Shang

Language models (LMs) are pretrained to imitate internet text, including content that would violate human preferences if generated by an LM: falsehoods, offensive comments, personally identifiable information, low-quality or buggy code, and…

Computation and Language · Computer Science 2023-06-16 Tomasz Korbak , Kejian Shi , Angelica Chen , Rasika Bhalerao , Christopher L. Buckley , Jason Phang , Samuel R. Bowman , Ethan Perez

Large pre-trained language models are successfully being used in a variety of tasks, across many languages. With this ever-increasing usage, the risk of harmful side effects also rises, for example by reproducing and reinforcing…

Computation and Language · Computer Science 2022-09-19 Pieter Delobelle , Bettina Berendt

While Reinforcement Learning (RL) has been proven essential for tuning large language models (LLMs), it can lead to reward over-optimization (ROO). Existing approaches address ROO by adding KL regularization, requiring computationally…

Computation and Language · Computer Science 2024-05-01 Mathieu Rita , Florian Strub , Rahma Chaabouni , Paul Michel , Emmanuel Dupoux , Olivier Pietquin

While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer…

Computation and Language · Computer Science 2026-01-21 Truong Nguyen , Phi Van Dat , Ngan Nguyen , Linh Ngo Van , Trung Le , Thanh Hong Nguyen

Knowledge distillation (KD) is an established paradigm for transferring privileged knowledge from a cumbersome model to a lightweight and efficient one. In recent years, logit-based KD methods are quickly catching up in performance with…

Computer Vision and Pattern Recognition · Computer Science 2024-12-24 Weijia Zhang , Dongnan Liu , Weidong Cai , Chao Ma

Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by leveraging Contrastive Learning, Intermediate Layer…

Computation and Language · Computer Science 2022-04-19 Md Akmal Haidar , Mehdi Rezagholizadeh , Abbas Ghaddar , Khalil Bibi , Philippe Langlais , Pascal Poupart

Language models (LMs) trained on vast quantities of text data can acquire sophisticated skills such as generating summaries, answering questions or generating code. However, they also manifest behaviors that violate human preferences, e.g.,…

Machine Learning · Computer Science 2024-04-19 Tomasz Korbak

Reinforcement learning (RL) is a promising approach for aligning large language models (LLMs) knowledge with sequential decision-making tasks. However, few studies have thoroughly investigated the impact on LLM agents capabilities of…

A huge number of multi-participant dialogues happen online every day, which leads to difficulty in understanding the nature of dialogue dynamics for both humans and machines. Dialogue disentanglement aims at separating an entangled dialogue…

Computation and Language · Computer Science 2023-02-17 Jingsheng Gao , Zeyu Li , Suncheng Xiang , Ting Liu , Yuzhuo Fu

Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the…

Computation and Language · Computer Science 2026-05-29 Zizhuo Lin , Quanling Liu , Jinsheng Quan , Chao Zhang , Yifan Zhu , Xing Shi , Jingtao Xu , Zhihui Li , Yawei Luo

Recent advances in Score Distillation Sampling (SDS) have improved 3D human generation from textual descriptions. However, existing methods still face challenges in accurately aligning 3D models with long and complex textual inputs. To…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Pengfei Zhou , Xukun Shen , Yong Hu

Learning from preference labels plays a crucial role in fine-tuning large language models. There are several distinct approaches for preference fine-tuning, including supervised learning, on-policy reinforcement learning (RL), and…

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

Large language models have led to significant progress across many NLP tasks, although their massive sizes often incur substantial computational costs. Distillation has become a common practice to compress these large and highly capable…

Computation and Language · Computer Science 2026-01-06 Zishun Yu , Shangzhe Li , Xinhua Zhang

Despite the recent success of deep neural networks, there remains a need for effective methods to enhance domain generalization using vision transformers. In this paper, we propose a novel domain generalization technique called Robust…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Ankur Singh , Senthilnath Jayavelu

Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs. Underspecified preferences could obscure directions…

Computation and Language · Computer Science 2024-03-22 Kyungjae Lee , Dasol Hwang , Sunghyun Park , Youngsoo Jang , Moontae Lee

Aligning large language models (LLMs) with human preferences is critical to recent advances in generative artificial intelligence. Reinforcement learning from human feedback (RLHF) is widely applied to achieve this objective. A key step in…

Machine Learning · Statistics 2025-01-03 Pangpang Liu , Chengchun Shi , Will Wei Sun

Large Language Models (LLMs) have exhibited remarkable performance across various natural language processing (NLP) tasks. However, fine-tuning these models often necessitates substantial supervision, which can be expensive and…

Computation and Language · Computer Science 2023-05-25 Jing-Cheng Pang , Pengyuan Wang , Kaiyuan Li , Xiong-Hui Chen , Jiacheng Xu , Zongzhang Zhang , Yang Yu

Cross-modality distillation arises as an important topic for data modalities containing limited knowledge such as depth maps and high-quality sketches. Such techniques are of great importance, especially for memory and privacy-restricted…

Machine Learning · Computer Science 2024-05-29 Hangyu Lin , Chen Liu , Chengming Xu , Zhengqi Gao , Yanwei Fu , Yuan Yao