Hindsight: Posterior-guided training of retrievers for improved open-ended generation

• URL: http://arxiv.org/abs/2110.07752v1
• Date: Thu, 14 Oct 2021 22:24:57 GMT
• Title: Hindsight: Posterior-guided training of retrievers for improved open-ended generation
• Authors: Ashwin Paranjape, Omar Khattab, Christopher Potts, Matei Zaharia, Christopher D. Manning
• Abstract summary: We propose an additional guide retriever that is allowed to use the target output and "in hindsight" retrieve relevant passages during training. For informative conversations from the Wizard of Wikipedia dataset, with posterior-guided training, the retriever finds passages with higher relevance in the top-10.
• Score: 41.59136233128446
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many text generation systems benefit from using a retriever to retrieve passages from a textual knowledge corpus (e.g., Wikipedia) which are then provided as additional context to the generator. For open-ended generation tasks (like generating informative utterances in conversations) many varied passages may be equally relevant and we find that existing methods that jointly train the retriever and generator underperform: the retriever may not find relevant passages even amongst the top-10 and hence the generator may not learn a preference to ground its generated output in them. We propose using an additional guide retriever that is allowed to use the target output and "in hindsight" retrieve relevant passages during training. We model the guide retriever after the posterior distribution Q of passages given the input and the target output and train it jointly with the standard retriever and the generator by maximizing the evidence lower bound (ELBo) in expectation over Q. For informative conversations from the Wizard of Wikipedia dataset, with posterior-guided training, the retriever finds passages with higher relevance in the top-10 (23% relative improvement), the generator's responses are more grounded in the retrieved passage (19% relative improvement) and the end-to-end system produces better overall output (6.4% relative improvement).

Related papers

• When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR [32.5131152148767]
  We propose a novel task of predicting whether a corpus is out-of-distribution (OOD) relative to a dense retriever before indexing.<n>We introduce GradNormIR, an unsupervised approach that leverages gradient norms to detect OOD corpora effectively.<n>Experiments on the BEIR benchmark demonstrate that GradNormIR enables timely updates of dense retrievers in evolving document collections.
  arXiv  Detail & Related papers  (2025-06-02T17:06:35Z)
• ReasonIR: Training Retrievers for Reasoning Tasks [139.54343970560103]
  ReasonIR-8B is the first retriever specifically trained for general reasoning tasks. It achieves a new state-of-the-art of 29.9 nDCG@10 without reranker and 36.9 nDCG@10 with reranker on BRIGHT, a widely-used information retrieval benchmark.
  arXiv  Detail & Related papers  (2025-04-29T09:49:28Z)
• Training a Utility-based Retriever Through Shared Context Attribution for Retrieval-Augmented Language Models [51.608246558235166]
  SCARLet is a framework for training utility-based retrievers in RALMs. It incorporates two key factors, multi-task generalization and inter-passage interaction. We evaluate our approach on ten datasets across various tasks, both in-domain and out-of-domain.
  arXiv  Detail & Related papers  (2025-04-01T09:28:28Z)
• Improving Retrieval-Augmented Code Comment Generation by Retrieving for Generation [3.123049150077741]
  We propose a novel training strategy to enable the retriever to learn from the feedback of the generator and retrieve exemplars for generation. By aligning high-score exemplars retrieved by the retriever with low-loss exemplars observed by the generator, the retriever can learn to retrieve exemplars that can best improve the quality of the generated comments.
  arXiv  Detail & Related papers  (2024-08-07T08:32:55Z)
• RLCoder: Reinforcement Learning for Repository-Level Code Completion [39.38066628941757]
  Repository-level code completion aims to generate code for unfinished code snippets within the context of a specified repository. Existing approaches mainly rely on retrieval-augmented generation strategies due to limitations in input sequence length. We propose RLCoder, a novel reinforcement learning framework, which can enable the retriever to learn to retrieve useful content for code completion without the need for labeled data.
  arXiv  Detail & Related papers  (2024-07-28T12:47:20Z)
• Blended RAG: Improving RAG (Retriever-Augmented Generation) Accuracy with Semantic Search and Hybrid Query-Based Retrievers [0.0]
  Retrieval-Augmented Generation (RAG) is a prevalent approach to infuse a private knowledge base of documents with Large Language Models (LLM) to build Generative Q&A (Question-Answering) systems. We propose the 'Blended RAG' method of leveraging semantic search techniques, such as Vector indexes and Sparse indexes, blended with hybrid query strategies. Our study achieves better retrieval results and sets new benchmarks for IR (Information Retrieval) datasets like NQ and TREC-COVID datasets.
  arXiv  Detail & Related papers  (2024-03-22T17:13:46Z)
• Retrieval-Generation Alignment for End-to-End Task-Oriented Dialogue System [40.33178881317882]
  We propose the application of maximal marginal likelihood to train a perceptive retriever by utilizing signals from response generation for supervision. We evaluate our approach on three task-oriented dialogue datasets using T5 and ChatGPT as the backbone models.
  arXiv  Detail & Related papers  (2023-10-13T06:03:47Z)
• Optimizing Factual Accuracy in Text Generation through Dynamic Knowledge Selection [71.20871905457174]
  Language models (LMs) have revolutionized the way we interact with information, but they often generate nonfactual text. Previous methods use external knowledge as references for text generation to enhance factuality but often struggle with the knowledge mix-up of irrelevant references. We present DKGen, which divide the text generation process into an iterative process.
  arXiv  Detail & Related papers  (2023-08-30T02:22:40Z)
• GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking [42.98064495920065]
  We propose the GeneRative Knowledge Improved Passage Ranking (GripRank) approach for knowledge-intensive language tasks. The GPE is a generative language model used to measure how likely the candidate passages can generate the proper answer. We conduct experiments on four datasets across three knowledge-intensive language tasks.
  arXiv  Detail & Related papers  (2023-05-29T15:15:53Z)
• Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy [164.83371924650294]
  We show that strong performance can be achieved by a method we call Iter-RetGen, which synergizes retrieval and generation in an iterative manner. A model output shows what might be needed to finish a task, and thus provides an informative context for retrieving more relevant knowledge. Iter-RetGen processes all retrieved knowledge as a whole and largely preserves the flexibility in generation without structural constraints.
  arXiv  Detail & Related papers  (2023-05-24T16:17:36Z)
• ReFIT: Relevance Feedback from a Reranker during Inference [109.33278799999582]
  Retrieve-and-rerank is a prevalent framework in neural information retrieval. We propose to leverage the reranker to improve recall by making it provide relevance feedback to the retriever at inference time.
  arXiv  Detail & Related papers  (2023-05-19T15:30:33Z)
• Active Retrieval Augmented Generation [123.68874416084499]
  Augmenting large language models (LMs) by retrieving information from external knowledge resources is one promising solution. Most existing retrieval augmented LMs employ a retrieve-and-generate setup that only retrieves information once based on the input. We propose Forward-Looking Active REtrieval augmented generation (FLARE), a generic method which iteratively uses a prediction of the upcoming sentence to anticipate future content.
  arXiv  Detail & Related papers  (2023-05-11T17:13:40Z)
• Learning to Retrieve Passages without Supervision [58.31911597824848]
  Dense retrievers for open-domain question answering (ODQA) have been shown to achieve impressive performance by training on large datasets of question-passage pairs. We investigate whether dense retrievers can be learned in a self-supervised fashion, and applied effectively without any annotations.
  arXiv  Detail & Related papers  (2021-12-14T19:18:08Z)

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.