paper-with-me

홈 › Papers

DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging

2024-07-01 · Tzu-Han Lin, Chen-An Li, Hung-Yi Lee, Yun-Nung Chen

Reinforcement learning from human feedback (RLHF) is a popular strategy for aligning large language models (LLMs) with desired behaviors. Reward modeling is a crucial step in RLHF. However, collecting paired preference data for training reward models is often costly and time-consuming, especially for domain-specific preferences requiring expert annotation. To address this challenge, we propose the \textbf{Do}main knowled\textbf{ge} merged \textbf{R}eward \textbf{M}odel (DogeRM), a novel framework that integrates domain-specific knowledge into a general reward model by model merging. The experiments demonstrate that DogeRM enhances performance across different benchmarks and provide a detailed analysis showcasing the effects of model merging, showing the great potential of facilitating model alignment.

📄 PDF Abstract BibTeX arXiv:2407.01470

Code (1)

miulab/dogerm 공식 구현 pytorch

Similar Papers 제목 키워드 기반

The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?

2026-03-03 · Yirong Zeng, Shen You, Yufei Liu, Qunyao Du 외 arxiv

Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon: tool overuse, the unnecessary tool-use during reasoning. In this p…

AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning

2025-12-18 · Tzu-Han Lin, Wei-Lin Chen, Chen-An Li, Hung-yi Lee 외 arxiv

Equipping large language models (LLMs) with search engines via reinforcement learning (RL) has emerged as an effective approach for building search agents. However, overreliance on search introduces unnecessary cost and …

Reinforcement LearningQuestion Answering

On Generalizing Beyond Domains in Cross-Domain Continual Learning

2022-03-08 · CVPR 2022 1 · Christian Simon, Masoud Faraki, Yi-Hsuan Tsai, Xiang Yu 외

Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task. Many recen…

Continual LearningKnowledge Distillation

MemSFT: Mitigating Alignment Tax with an External Parametric Memory

2026-07-28 · Jiarui Wang, Xiang Shi, Jiaqi Cao, Rubin Wei 외 arxiv

Adapting Large Language Models (LLMs) to specialized domains often incurs an alignment tax, as fine-tuning on domain-specific tasks can cause catastrophic forgetting and substantially degrade performance on general tasks…

World Value Functions: Knowledge Representation for Learning and Planning

2022-06-23 · Geraud Nangue Tasse, Benjamin Rosman, Steven James

We propose world value functions (WVFs), a type of goal-oriented general value function that represents how to solve not just a given task, but any other goal-reaching task in an agent's environment. This is achieved by …