Self-Consistency Preference Optimization

• URL: http://arxiv.org/abs/2411.04109v2
• Date: Thu, 07 Nov 2024 23:41:00 GMT
• Title: Self-Consistency Preference Optimization
• Authors: Archiki Prasad, Weizhe Yuan, Richard Yuanzhe Pang, Jing Xu, Maryam Fazel-Zarandi, Mohit Bansal, Sainbayar Sukhbaatar, Jason Weston, Jane Yu,
• Abstract summary: We introduce self-consistency preference optimization (ScPO) ScPO iteratively trains consistent answers to be preferred over inconsistent ones on unsupervised new problems. On ZebraLogic, ScPO fine Llamatunes-3 8B to be superior to Llama-3 70B, Gemma-2 27B, and Claude-3 Haiku.
• Score: 79.37880123635405
• License:
• Abstract: Self-alignment, whereby models learn to improve themselves without human annotation, is a rapidly growing research area. However, existing techniques often fail to improve complex reasoning tasks due to the difficulty of assigning correct rewards. An orthogonal approach that is known to improve correctness is self-consistency, a method applied at inference time based on multiple sampling in order to find the most consistent answer. In this work, we extend the self-consistency concept to help train models. We thus introduce self-consistency preference optimization (ScPO), which iteratively trains consistent answers to be preferred over inconsistent ones on unsupervised new problems. We show ScPO leads to large improvements over conventional reward model training on reasoning tasks such as GSM8K and MATH, closing the gap with supervised training with gold answers or preferences, and that combining ScPO with standard supervised learning improves results even further. On ZebraLogic, ScPO finetunes Llama-3 8B to be superior to Llama-3 70B, Gemma-2 27B, and Claude-3 Haiku.

Related papers

• ACING: Actor-Critic for Instruction Learning in Black-Box Large Language Models [4.890873355984701]
  ACING is a task-specific prompt optimization approach framed as a stateless continuous-action Reinforcement Learning problem. We validate ACING by optimizing prompts for ChatGPT on 30 instruction-based tasks. ACING consistently outperforms baseline methods, achieving a median score improvement of 10 percentage points.
  arXiv  Detail & Related papers  (2024-11-19T18:58:03Z)
• Self-Training Meets Consistency: Improving LLMs' Reasoning with Consistency-Driven Rationale Evaluation [15.124701883286436]
  Self-training approach for large language models (LLMs) improves reasoning abilities by training the models on their self-generated rationales. Previous approaches have labeled rationales that produce correct answers for a given question as appropriate for training. We propose CREST (Consistency-driven Rationale Evaluation for Self-Training), a self-training framework that further evaluates each rationale through follow-up questions.
  arXiv  Detail & Related papers  (2024-11-10T08:11:05Z)
• Margin Matching Preference Optimization: Enhanced Model Alignment with Granular Feedback [64.67540769692074]
  Large language models (LLMs) fine-tuned with alignment techniques, such as reinforcement learning from human feedback, have been instrumental in developing some of the most capable AI systems to date. We introduce an approach called Margin Matching Preference Optimization (MMPO), which incorporates relative quality margins into optimization, leading to improved LLM policies and reward models. Experiments with both human and AI feedback data demonstrate that MMPO consistently outperforms baseline methods, often by a substantial margin, on popular benchmarks including MT-bench and RewardBench.
  arXiv  Detail & Related papers  (2024-10-04T04:56:11Z)
• Training Language Models to Self-Correct via Reinforcement Learning [98.35197671595343]
  Self-correction has been found to be largely ineffective in modern large language models (LLMs) We develop a multi-turn online reinforcement learning approach, SCoRe, that significantly improves an LLM's self-correction ability using entirely self-generated data. We find that SCoRe achieves state-of-the-art self-correction performance, improving the base models' self-correction by 15.6% and 9.1% respectively on MATH and HumanEval.
  arXiv  Detail & Related papers  (2024-09-19T17:16:21Z)
• Self-Taught Evaluators [77.92610887220594]
  We present an approach that aims to im-proves without human annotations, using synthetic training data only. Our Self-Taught Evaluator can improve a strong LLM from 75.4 to 88.3 on RewardBench.
  arXiv  Detail & Related papers  (2024-08-05T17:57:02Z)
• Prior Constraints-based Reward Model Training for Aligning Large Language Models [58.33118716810208]
  This paper proposes a Prior Constraints-based Reward Model (namely PCRM) training method to mitigate this problem. PCRM incorporates prior constraints, specifically, length ratio and cosine similarity between outputs of each comparison pair, during reward model training to regulate optimization magnitude and control score margins. Experimental results demonstrate that PCRM significantly improves alignment performance by effectively constraining reward score scaling.
  arXiv  Detail & Related papers  (2024-04-01T07:49:11Z)
• Self-Labeling the Job Shop Scheduling Problem [15.723699332053558]
  We show that generative models can be trained by sampling multiple solutions and using the best one according to the problem objective as a pseudo-label. We prove the robustness of SLIM to various parameters and its generality by applying it to the Traveling Salesman Problem.
  arXiv  Detail & Related papers  (2024-01-22T11:08:36Z)
• Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning [70.65666982566655]
  Permutation flow shop scheduling (PFSS) is widely used in manufacturing systems. We propose to train the model via expert-driven imitation learning, which accelerates convergence more stably and accurately. Our model's network parameters are reduced to only 37% of theirs, and the solution gap of our model towards the expert solutions decreases from 6.8% to 1.3% on average.
  arXiv  Detail & Related papers  (2022-10-31T09:46:26Z)

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.