Gumbel Reranking: Differentiable End-to-End Reranker Optimization

• URL: http://arxiv.org/abs/2502.11116v1
• Date: Sun, 16 Feb 2025 13:23:39 GMT
• Title: Gumbel Reranking: Differentiable End-to-End Reranker Optimization
• Authors: Siyuan Huang, Zhiyuan Ma, Jintao Du, Changhua Meng, Weiqiang Wang, Jingwen Leng, Minyi Guo, Zhouhan Lin,
• Abstract summary: RAG systems rely on rerankers to identify relevant documents. fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. We propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap.
• Score: 61.16471123356738
• License:
• Abstract: RAG systems rely on rerankers to identify relevant documents. However, fine-tuning these models remains challenging due to the scarcity of annotated query-document pairs. Existing distillation-based approaches suffer from training-inference misalignment and fail to capture interdependencies among candidate documents. To overcome these limitations, we reframe the reranking process as an attention-mask problem and propose Gumbel Reranking, an end-to-end training framework for rerankers aimed at minimizing the training-inference gap. In our approach, reranker optimization is reformulated as learning a stochastic, document-wise Top-$k$ attention mask using the Gumbel Trick and Relaxed Top-$k$ Sampling. This formulation enables end-to-end optimization by minimizing the overall language loss. Experiments across various settings consistently demonstrate performance gains, including a 10.4\% improvement in recall on HotpotQA for distinguishing indirectly relevant documents.

Related papers

• Towards Generalizable Trajectory Prediction Using Dual-Level Representation Learning And Adaptive Prompting [107.4034346788744]
  Existing vehicle trajectory prediction models struggle with generalizability, prediction uncertainties, and handling complex interactions. We propose Perceiver with Register queries (PerReg+), a novel trajectory prediction framework that introduces: (1) Dual-Level Representation Learning via Self-Distillation (SD) and Masked Reconstruction (MR), capturing global context and fine-grained details; (2) Enhanced Multimodality using register-based queries and pretraining, eliminating the need for clustering and suppression; and (3) Adaptive Prompt Tuning during fine-tuning, freezing the main architecture and optimizing a small number of prompts for efficient adaptation.
  arXiv  Detail & Related papers  (2025-01-08T20:11:09Z)
• A Minimal Subset Approach for Efficient and Scalable Loop Closure [7.066382982173528]
  Loop detection in large-scale and long-term missions can be computationally demanding. Keyframe sampling mitigates this by reducing the number of frames stored and processed in the back-end system. In this article, we address the gap in optimized sampling for the combined problem of pose graph optimization and loop closure detection.
  arXiv  Detail & Related papers  (2025-01-03T12:48:01Z)
• Self-Calibrated Listwise Reranking with Large Language Models [137.6557607279876]
  Large language models (LLMs) have been employed in reranking tasks through a sequence-to-sequence approach. This reranking paradigm requires a sliding window strategy to iteratively handle larger candidate sets. We propose a novel self-calibrated listwise reranking method, which aims to leverage LLMs to produce global relevance scores for ranking.
  arXiv  Detail & Related papers  (2024-11-07T10:31:31Z)
• Quam: Adaptive Retrieval through Query Affinity Modelling [15.3583908068962]
  Building relevance models to rank documents based on user information needs is a central task in information retrieval and the NLP community. We propose a unifying view of the nascent area of adaptive retrieval by proposing, Quam. Our proposed approach, Quam improves the recall performance by up to 26% over the standard re-ranking baselines.
  arXiv  Detail & Related papers  (2024-10-26T22:52:12Z)
• RaFe: Ranking Feedback Improves Query Rewriting for RAG [83.24385658573198]
  We propose a framework for training query rewriting models free of annotations. By leveraging a publicly available reranker, oursprovides feedback aligned well with the rewriting objectives.
  arXiv  Detail & Related papers  (2024-05-23T11:00:19Z)
• Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation [63.180725016463974]
  Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. We introduce a novel noisy correspondence learning framework, namely textbfSelf-textbfReinforcing textbfErrors textbfMitigation (SREM)
  arXiv  Detail & Related papers  (2023-12-27T09:03:43Z)
• Fine-grained Retrieval Prompt Tuning [149.9071858259279]
  Fine-grained Retrieval Prompt Tuning steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompt and feature adaptation. Our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets.
  arXiv  Detail & Related papers  (2022-07-29T04:10:04Z)
• Pattern-aware Data Augmentation for Query Rewriting in Voice Assistant Systems [10.332550622090718]
  We propose an augmentation framework that learns patterns from existing training pairs and generates rewrite candidates from rewrite labels inversely to compensate for insufficient QR training data. Our experimental results show its effectiveness compared with a fully trained QR baseline and demonstrate its potential application in boosting the QR performance on low-resource domains or locales.
  arXiv  Detail & Related papers  (2020-12-21T16:36:32Z)

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.