Extensive Self-Contrast Enables Feedback-Free Language Model Alignment

• URL: http://arxiv.org/abs/2404.00604v1
• Date: Sun, 31 Mar 2024 08:30:15 GMT
• Title: Extensive Self-Contrast Enables Feedback-Free Language Model Alignment
• Authors: Xiao Liu, Xixuan Song, Yuxiao Dong, Jie Tang,
• Abstract summary: Self-Contrast is a feedback-free large language model alignment method via exploiting extensive self-generated negatives. With only supervised fine-tuning (SFT) targets, Self-Contrast harnesses a pre-trained embedding model to filter multiple negatives according to text similarity. Our experiments with direct preference optimization (DPO) on three datasets show that, Self-Contrast could consistently outperform SFT and standard DPO training by large margins.
• Score: 29.268993281961695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 stymie its wider applications. In this work, we introduce Self-Contrast, a feedback-free large language model alignment method via exploiting extensive self-generated negatives. With only supervised fine-tuning (SFT) targets, Self-Contrast leverages the LLM itself to generate massive diverse candidates, and harnesses a pre-trained embedding model to filter multiple negatives according to text similarity. Theoretically, we illustrate that in this setting, merely scaling negative responses can still effectively approximate situations with more balanced positive and negative preference annotations. Our experiments with direct preference optimization (DPO) on three datasets show that, Self-Contrast could consistently outperform SFT and standard DPO training by large margins. And as the number of self-generated negatives increases, the performance of Self-Contrast continues to grow. Code and data are available at https://github.com/THUDM/Self-Contrast.

Related papers

• Aligning Large Language Models via Fully Self-Synthetic Data [20.05693955243206]
  Traditional reinforcement learning from human feedback (RLHF) for large language models (LLMs) relies on expensive human-annotated datasets.<n>In this work, we introduce Self-Alignment Optimization (SAO), a fully self-synthetic framework for LLM alignment.<n>Experiments demonstrate that SAO effectively enhances the model's chat capabilities on standard benchmarks like AlpacaEval2.0.
  arXiv  Detail & Related papers  (2025-10-08T05:07:45Z)
• Negative-Guided Subject Fidelity Optimization for Zero-Shot Subject-Driven Generation [41.88237450556626]
  We present Subject Fidelity Optimization (SFO), a novel comparative learning framework for zero-shot subject-driven generation.<n>For negative targets, we propose Condition-Degradation Negative Sampling (CDNS), which automatically generates distinctive and informative negatives.<n>Extensive experiments demonstrate that SFO with CDNS significantly outperforms baselines in terms of both subject fidelity and text alignment.
  arXiv  Detail & Related papers  (2025-06-04T06:59:25Z)
• Negative-Prompt-driven Alignment for Generative Language Model [34.191590966148816]
  We propose NEgative-prompt-driven AlignmenT to guide language models away from undesirable behaviors. NEAT explicitly penalizes the model for producing harmful outputs, guiding it not only toward desirable behaviors but also steering it away from generating undesirable, biased responses. Extensive experiments validate NEAT's effectiveness in significantly enhancing language models' alignment with human values and preferences.
  arXiv  Detail & Related papers  (2024-10-16T03:30:09Z)
• Just Say What You Want: Only-prompting Self-rewarding Online Preference Optimization [64.34767799614328]
  Current self-rewarding approaches rely heavily on the discriminator's judgment capabilities. We propose a novel, only-prompting self-rewarding online algorithm that generates preference datasets without relying on judgment capabilities.
  arXiv  Detail & Related papers  (2024-09-26T04:41:08Z)
• Aligning Large Language Models with Self-generated Preference Data [72.99676237703099]
  We propose a new framework that boosts the alignment of large language models (LLMs) with human preferences. Our key idea is leveraging the human prior knowledge within the small (seed) data. We introduce a noise-aware preference learning algorithm to mitigate the risk of low quality within generated preference data.
  arXiv  Detail & Related papers  (2024-06-06T18:01:02Z)
• Aligning Large Language Models via Fine-grained Supervision [20.35000061196631]
  Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current approaches focus on using reinforcement learning with human feedback to improve model alignment. We propose a method to enhance LLM alignment through fine-grained token-level supervision.
  arXiv  Detail & Related papers  (2024-06-04T20:21:45Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models [52.98743860365194]
  We propose a new fine-tuning method called Self-Play fIne-tuNing (SPIN) At the heart of SPIN lies a self-play mechanism, where the LLM refines its capability by playing against instances of itself. This sheds light on the promise of self-play, enabling the achievement of human-level performance in LLMs without the need for expert opponents.
  arXiv  Detail & Related papers  (2024-01-02T18:53:13Z)
• Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging [148.77027765872006]
  We study Reinforcement Learning from Personalized Human Feedback (RLPHF) problem. LLMs are aligned to multiple preferences by modeling alignment as a Multi-Objective Reinforcement Learning (MORL) problem. We show that we can achieve personalized alignment by decomposing preferences into multiple dimensions.
  arXiv  Detail & Related papers  (2023-10-17T20:22:13Z)
• Constructive Large Language Models Alignment with Diverse Feedback [76.9578950893839]
  We introduce Constructive and Diverse Feedback (CDF) as a novel method to enhance large language models alignment. We exploit critique feedback for easy problems, refinement feedback for medium problems, and preference feedback for hard problems. By training our model with this diversified feedback, we achieve enhanced alignment performance while using less training data.
  arXiv  Detail & Related papers  (2023-10-10T09:20:14Z)
• Training Language Models with Language Feedback at Scale [50.70091340506957]
  We introduce learning from Language Feedback (ILF), a new approach that utilizes more informative language feedback. ILF consists of three steps that are applied iteratively: first, conditioning the language model on the input, an initial LM output, and feedback to generate refinements. We show theoretically that ILF can be viewed as Bayesian Inference, similar to Reinforcement Learning from human feedback.
  arXiv  Detail & Related papers  (2023-03-28T17:04:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.