Learning to Search Effective Example Sequences for In-Context Learning

• URL: http://arxiv.org/abs/2503.08030v1
• Date: Tue, 11 Mar 2025 04:24:59 GMT
• Title: Learning to Search Effective Example Sequences for In-Context Learning
• Authors: Xiang Gao, Ankita Sinha, Kamalika Das,
• Abstract summary: We introduce Beam Search-based Example Sequence Constructor (BESC), a novel method for learning to construct optimal example sequences.<n>BESC addresses all key factors involved in sequence selection by considering them jointly during inference, while incrementally building the sequence.<n> Experiments across various datasets and language models show notable improvements in performance.
• Score: 6.532919612658209
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) demonstrate impressive few-shot learning capabilities, but their performance varies widely based on the sequence of in-context examples. Key factors influencing this include the sequence's length, composition, and arrangement, as well as its relation to the specific query. Existing methods often tackle these factors in isolation, overlooking their interdependencies. Moreover, the extensive search space for selecting optimal sequences complicates the development of a holistic approach. In this work, we introduce Beam Search-based Example Sequence Constructor (BESC), a novel method for learning to construct optimal example sequences. BESC addresses all key factors involved in sequence selection by considering them jointly during inference, while incrementally building the sequence. This design enables the use of beam search to significantly reduce the complexity of the search space. Experiments across various datasets and language models show notable improvements in performance.

Related papers

• Reinforcing Compositional Retrieval: Retrieving Step-by-Step for Composing Informative Contexts [67.67746334493302]
  Large Language Models (LLMs) have demonstrated remarkable capabilities across numerous tasks, yet they often rely on external context to handle complex tasks. We propose a tri-encoder sequential retriever that models this process as a Markov Decision Process (MDP) We show that our method consistently and significantly outperforms baselines, underscoring the importance of explicitly modeling inter-example dependencies.
  arXiv  Detail & Related papers  (2025-04-15T17:35:56Z)
• Retrieval with Learned Similarities [2.729516456192901]
  State-of-the-art retrieval algorithms have migrated to learned similarities.<n>We show that Mixture-of-Logits (MoL) can be realized empirically to achieve superior performance on diverse retrieval scenarios.
  arXiv  Detail & Related papers  (2024-07-22T08:19:34Z)
• Relation-aware Ensemble Learning for Knowledge Graph Embedding [68.94900786314666]
  We propose to learn an ensemble by leveraging existing methods in a relation-aware manner. exploring these semantics using relation-aware ensemble leads to a much larger search space than general ensemble methods. We propose a divide-search-combine algorithm RelEns-DSC that searches the relation-wise ensemble weights independently.
  arXiv  Detail & Related papers  (2023-10-13T07:40:12Z)
• 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)
• Finding Support Examples for In-Context Learning [73.90376920653507]
  We propose LENS, a fiLter-thEN-Search method to tackle this challenge in two stages. First we filter the dataset to obtain informative in-context examples individually. Then we propose diversity-guided example search which iteratively refines and evaluates the selected example permutations.
  arXiv  Detail & Related papers  (2023-02-27T06:32:45Z)
• Deep Learning on Attributed Sequences [0.38707695363745215]
  We focus on analyzing and building deep learning models for four new problems on attributed sequences. Our experiments on real-world datasets demonstrate that the proposed solutions significantly improve the performance of each task.
  arXiv  Detail & Related papers  (2022-01-23T06:54:31Z)
• Determinantal Beam Search [75.84501052642361]
  Beam search is a go-to strategy for decoding neural sequence models. In use-cases that call for multiple solutions, a diverse or representative set is often desired. By posing iterations in beam search as a series of subdeterminant problems, we can turn the algorithm into a diverse subset selection process.
  arXiv  Detail & Related papers  (2021-06-14T13:01:46Z)
• Joint Contrastive Learning with Infinite Possibilities [114.45811348666898]
  This paper explores useful modifications of the recent development in contrastive learning via novel probabilistic modeling. We derive a particular form of contrastive loss named Joint Contrastive Learning (JCL)
  arXiv  Detail & Related papers  (2020-09-30T16:24:21Z)

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.