From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation

• URL: http://arxiv.org/abs/2502.00330v1
• Date: Sat, 01 Feb 2025 06:23:24 GMT
• Title: From Few to Many: Self-Improving Many-Shot Reasoners Through Iterative Optimization and Generation
• Authors: Xingchen Wan, Han Zhou, Ruoxi Sun, Hootan Nakhost, Ke Jiang, Sercan Ö. Arık,
• Abstract summary: Many-shot in-context learning (ICL) can lead to performance benefits, but it is unclear what aspects dominate the benefits and whether simply scaling to more examples is the most effective way of improving ICL. We propose BRIDGE, an algorithm that alternates between the optimize step with Bayesian optimization to discover the influential sets of examples and the generate step to reuse this set to expand the reasoning paths of the examples back to the many-shot regime automatically. On Gemini, Claude, and Mistral LLMs of different sizes, we show that BRIDGE to significant improvements across a diverse set of tasks, including
• Score: 18.988069926846357
• License:
• Abstract: Recent advances in long-context large language models (LLMs) have led to the emerging paradigm of many-shot in-context learning (ICL), where it is observed that scaling many more demonstrating examples beyond the conventional few-shot setup in the context can lead to performance benefits. However, despite its promise, it is unclear what aspects dominate the benefits and whether simply scaling to more examples is the most effective way of improving many-shot ICL. In this work, we first provide an analysis of the factors driving many-shot ICL, and we find that 1) many-shot performance can still be attributed to often a few disproportionately influential examples and 2) identifying such influential examples ("optimize") and using them as demonstrations to regenerate new examples ("generate") can lead to further improvements. Inspired by the findings, we propose BRIDGE, an algorithm that alternates between the optimize step with Bayesian optimization to discover the influential sets of examples and the generate step to reuse this set to expand the reasoning paths of the examples back to the many-shot regime automatically. On Gemini, Claude, and Mistral LLMs of different sizes, we show that BRIDGE to significant improvements across a diverse set of tasks, including symbolic reasoning, numerical reasoning, and code generation.

Related papers

• More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives [50.772462704559345]
  We introduce DrICL, a novel optimization method that enhances model performance through Differentiated Learning and advantage-based Reweighting objectives. Globally, DrICL utilizes differentiated learning to optimize the NLL objective, ensuring that many-shot performance surpasses zero-shot levels. We develop the Many-Shot ICL Benchmark (ICL-50)-a large-scale benchmark of 50 tasks that cover shot numbers from 1 to 350 within sequences of up to 8,000 tokens-for fine-tuning purposes.
  arXiv  Detail & Related papers  (2025-01-07T14:57:08Z)
• Evolutionary Pre-Prompt Optimization for Mathematical Reasoning [45.461506988071534]
  This paper explores the optimization of example selection for designing effective chain-of-thought pre-prompts. It shows that the choice of the algorithm, typically in favor of comparison-based methods such as evolutionary computation, significantly enhances efficacy and feasibility.
  arXiv  Detail & Related papers  (2024-12-05T16:12:06Z)
• Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning [19.16587730306472]
  In-Context Learning (ICL) emerges as a key feature for Large Language Models (LLMs) We propose Logit Arithmetic Reweighting Approach (LARA), a novel framework that enhances ICL by using logit-based ensembling of multiple demonstrations.
  arXiv  Detail & Related papers  (2024-10-14T01:34:16Z)
• Large Language Models Know What Makes Exemplary Contexts [42.90814615222177]
  In-context learning (ICL) has proven to be a significant capability with the advancement of Large Language models (LLMs) This paper presents a unified framework for LLMs that allows them to self-select influential in-context examples to compose their contexts.
  arXiv  Detail & Related papers  (2024-08-14T12:32:41Z)
• Many-Shot In-Context Learning [58.395589302800566]
  Large language models (LLMs) excel at few-shot in-context learning (ICL) We observe significant performance gains across a wide variety of generative and discriminative tasks. Unlike few-shot learning, many-shot learning is effective at overriding pretraining biases.
  arXiv  Detail & Related papers  (2024-04-17T02:49:26Z)
• ParaICL: Towards Robust Parallel In-Context Learning [74.38022919598443]
  Large language models (LLMs) have become the norm in natural language processing. Few-shot in-context learning (ICL) relies on the choice of few-shot demonstration examples. We propose a novel method named parallel in-context learning (ParaICL)
  arXiv  Detail & Related papers  (2024-03-31T05:56:15Z)
• Retrieval-augmented Multi-modal Chain-of-Thoughts Reasoning for Large Language Models [56.256069117502385]
  Chain of Thought (CoT) approaches can be used to enhance the capability of Large Language Models (LLMs) on complex reasoning tasks. However, the selection of optimal CoT demonstration examples in multi-modal reasoning remains less explored. We introduce a novel approach that addresses this challenge by using retrieval mechanisms to automatically select demonstration examples.
  arXiv  Detail & Related papers  (2023-12-04T08:07:21Z)
• RetICL: Sequential Retrieval of In-Context Examples with Reinforcement Learning [53.52699766206808]
  We propose Retrieval for In-Context Learning (RetICL), a learnable method for modeling and optimally selecting examples sequentially for in-context learning. We evaluate RetICL on math word problem solving and scientific question answering tasks and show that it consistently outperforms or matches and learnable baselines.
  arXiv  Detail & Related papers  (2023-05-23T20:15:56Z)
• Large Language Model Programs [74.31873455763275]
  In recent years, large pre-trained language models (LLMs) have demonstrated the ability to follow instructions and perform novel tasks from a few examples. We extend this line of reasoning and present a method which further expands the capabilities of an LLM by embedding it within an algorithm or program. We obtain a 6.4% improvement over the chain of thought baseline through a more algorithmic approach without any finetuning.
  arXiv  Detail & Related papers  (2023-05-09T11:55:36Z)

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.