paper-with-me

Papers

Direct Large Language Model Alignment Through Self-Rewarding Contrastive Prompt Distillation

2024-02-19 · Aiwei Liu, Haoping Bai, Zhiyun Lu, Xiang Kong, Simon Wang, Jiulong Shan, Meng Cao, Lijie Wen

Aligning large language models (LLMs) with human expectations without human-annotated preference data is an important problem. In this paper, we propose a method to evaluate the response preference by using the output probabilities of response pairs under contrastive prompt pairs, which could achieve better performance on LLaMA2-7B and LLaMA2-13B compared to RLAIF. Based on this, we propose an automatic alignment method, Direct Large Model Alignment (DLMA). First, we use contrastive prompt pairs to automatically generate preference data. Then, we continue to evaluate the generated preference data using contrastive prompt pairs and calculate a self-rewarding score. Finally, we use the DPO algorithm to effectively align LLMs by combining this self-rewarding score. In the experimental stage, our DLMA method could surpass the \texttt{RLHF} method without relying on human-annotated preference data.

📄 PDF Abstract BibTeX arXiv:2402.11907

Code (1)

exlaw/dlma 공식 구현 pytorch

Tasks

Language ModelingLanguage ModellingLarge Language Model

Methods 이 논문이 사용한 방법론

DPO 설명 없음
RLAIF 설명 없음
ALIGN In the ALIGN method, visual and language representations are jointly trained from noisy image alt-text data. The image and text encoders are learned via contrastive loss…

Similar Papers 제목 키워드 기반

Smaller Large Language Models Can Do Moral Self-Correction

2024-10-30 · Guangliang Liu, Zhiyu Xue, Rongrong Wang, Kristen Marie Johnson

Self-correction is one of the most amazing emerging capabilities of Large Language Models (LLMs), enabling LLMs to self-modify an inappropriate output given a natural language feedback which describes the problems of tha…

Language ModelingLanguage ModellingSafety Alignment

Enhancing Visual-Language Modality Alignment in Large Vision Language Models via Self-Improvement

2024-05-24 · Xiyao Wang, Jiuhai Chen, Zhaoyang Wang, YuHang Zhou 외

Large vision-language models (LVLMs) have achieved impressive results in various visual question-answering and reasoning tasks through vision instruction tuning on specific datasets. However, there is still significant r…

HallucinationImage ComprehensionQuestion AnsweringVisual Question Answering

Extensive Self-Contrast Enables Feedback-Free Language Model Alignment

2024-03-31 · Xiao Liu, Xixuan Song, Yuxiao Dong, Jie Tang

Reinforcement learning from human feedback (RLHF) has been a central technique for recent large language model (LLM) alignment. However, its heavy dependence on costly human or LLM-as-Judge preference feedback could stym…

Language ModelingLanguage ModellingLarge Language Modeltext similarity

ContraSolver: Self-Alignment of Language Models by Resolving Internal Preference Contradictions

2024-06-13 · Xu Zhang, Xunjian Yin, Xiaojun Wan

While substantial advancements have been made in developing large language models (LLMs), achieving control over their behavior can be difficult. Direct preference optimization (DPO) assumes the existence of a latent rew…

A Single Neuron Is Sufficient to Bypass Safety Alignment in Large Language Models

2026-05-08 · Hamid Kazemi, Atoosa Chegini, Maria Safi arxiv

Safety alignment in language models operates through two mechanistically distinct systems: refusal neurons that gate whether harmful knowledge is expressed, and concept neurons that encode the harmful knowledge itself. B…

Prompt Engineering