In-Context Learning with Reinforcement Learning for Incomplete Utterance Rewriting

• URL: http://arxiv.org/abs/2408.13028v1
• Date: Fri, 23 Aug 2024 12:32:12 GMT
• Title: In-Context Learning with Reinforcement Learning for Incomplete Utterance Rewriting
• Authors: Haowei Du, Dongyan Zhao,
• Abstract summary: In-context learning of large language models (LLMs) makes predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL utilize sparse or dense retrievers and derive effective performance. We propose our policy-based reinforcement learning framework for example selection (RLS), which consists of a language model (LM) selector and an LLM generator.
• Score: 33.89176174108559
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In-context learning (ICL) of large language models (LLMs) has attracted increasing attention in the community where LLMs make predictions only based on instructions augmented with a few examples. Existing example selection methods for ICL utilize sparse or dense retrievers and derive effective performance. However, these methods do not utilize direct feedback of LLM to train the retriever and the examples selected can not necessarily improve the analogy ability of LLM. To tackle this, we propose our policy-based reinforcement learning framework for example selection (RLS), which consists of a language model (LM) selector and an LLM generator. The LM selector encodes the candidate examples into dense representations and selects the top-k examples into the demonstration for LLM. The outputs of LLM are adopted to compute the reward and policy gradient to optimize the LM selector. We conduct experiments on different datasets and significantly outperform existing example selection methods. Moreover, our approach shows advantages over supervised finetuning (SFT) models in few shot setting. Further experiments show the balance of abundance and the similarity with the test case of examples is important for ICL performance of LLM.

Related papers

• Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation [20.420575358183687]
  Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs) Previous approaches typically train retrievers based on semantic similarity, lacking optimization for RAG. We propose a novel framework, FiGRet, which leverages the language capabilities of LLMs to construct examples from a more granular, information-centric perspective.
  arXiv  Detail & Related papers  (2024-11-06T14:42:39Z)
• SelectLLM: Query-Aware Efficient Selection Algorithm for Large Language Models [8.558834738072363]
  Large language models (LLMs) have gained increased popularity due to their remarkable success across various tasks. However, individual LLMs have limitations when applied to complex tasks because of such factors as training biases, model sizes, and the datasets used. We introduce SelectLLM, a novel algorithm that directs input queries to the most suitable subset of LLMs from a large pool.
  arXiv  Detail & Related papers  (2024-08-16T06:11:21Z)
• 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)
• One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
  Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs) We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
  arXiv  Detail & Related papers  (2024-05-30T03:44:54Z)
• 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)
• The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning [61.68787689234622]
  A recent study, LIMA, shows that using merely 1K examples for alignment tuning can achieve significant alignment performance as well. This raises questions about how exactly the alignment tuning transforms a base LLM. We show that the gap between tuning-free and tuning-based alignment methods can be significantly reduced through strategic prompting.
  arXiv  Detail & Related papers  (2023-12-04T00:46:11Z)
• More Samples or More Prompts? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineering [35.086135550672864]
  We propose In-Context Sampling (ICS) to produce confident predictions by optimizing the construction of multiple ICL prompt inputs. An in-depth evaluation with three data similarity-based ICS strategies suggests that these strategies can further elevate LLM's performance.
  arXiv  Detail & Related papers  (2023-11-16T11:02:49Z)
• Which Examples to Annotate for In-Context Learning? Towards Effective and Efficient Selection [35.924633625147365]
  Large Language Models (LLMs) can adapt to new tasks via in-context learning (ICL) In this work, we investigate an active learning approach for ICL, where there is a limited budget for annotating examples. We propose a model-adaptive optimization-free algorithm, termed AdaICL, which identifies examples that the model is uncertain about.
  arXiv  Detail & Related papers  (2023-10-30T22:03:55Z)
• Reflection-Tuning: Data Recycling Improves LLM Instruction-Tuning [79.32236399694077]
  Low-quality data in the training set are usually detrimental to instruction tuning. We propose a novel method, termed "reflection-tuning" This approach utilizes an oracle LLM to recycle the original training data by introspecting and enhancing the quality of instructions and responses in the data.
  arXiv  Detail & Related papers  (2023-10-18T05:13:47Z)
• LLMRec: Benchmarking Large Language Models on Recommendation Task [54.48899723591296]
  The application of Large Language Models (LLMs) in the recommendation domain has not been thoroughly investigated. We benchmark several popular off-the-shelf LLMs on five recommendation tasks, including rating prediction, sequential recommendation, direct recommendation, explanation generation, and review summarization. The benchmark results indicate that LLMs displayed only moderate proficiency in accuracy-based tasks such as sequential and direct recommendation.
  arXiv  Detail & Related papers  (2023-08-23T16:32:54Z)
• Learning to Retrieve In-Context Examples for Large Language Models [69.9707552694766]
  Large language models (LLMs) have demonstrated their ability to learn in-context. The effectiveness of in-context learning is heavily reliant on the quality of the selected examples. We propose a novel framework to iteratively train dense retrievers that can identify high-quality in-context examples.
  arXiv  Detail & Related papers  (2023-07-14T05:23:08Z)

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.