FIRST: Faster Improved Listwise Reranking with Single Token Decoding
- URL: http://arxiv.org/abs/2406.15657v1
- Date: Fri, 21 Jun 2024 21:27:50 GMT
- Title: FIRST: Faster Improved Listwise Reranking with Single Token Decoding
- Authors: Revanth Gangi Reddy, JaeHyeok Doo, Yifei Xu, Md Arafat Sultan, Deevya Swain, Avirup Sil, Heng Ji,
- Abstract summary: First, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates.
Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark.
Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
- Score: 56.727761901751194
- License:
- Abstract: Large Language Models (LLMs) have significantly advanced the field of information retrieval, particularly for reranking. Listwise LLM rerankers have showcased superior performance and generalizability compared to existing supervised approaches. However, conventional listwise LLM reranking methods lack efficiency as they provide ranking output in the form of a generated ordered sequence of candidate passage identifiers. Further, they are trained with the typical language modeling objective, which treats all ranking errors uniformly--potentially at the cost of misranking highly relevant passages. Addressing these limitations, we introduce FIRST, a novel listwise LLM reranking approach leveraging the output logits of the first generated identifier to directly obtain a ranked ordering of the candidates. Further, we incorporate a learning-to-rank loss during training, prioritizing ranking accuracy for the more relevant passages. Empirical results demonstrate that FIRST accelerates inference by 50% while maintaining a robust ranking performance with gains across the BEIR benchmark. Finally, to illustrate the practical effectiveness of listwise LLM rerankers, we investigate their application in providing relevance feedback for retrievers during inference. Our results show that LLM rerankers can provide a stronger distillation signal compared to cross-encoders, yielding substantial improvements in retriever recall after relevance feedback.
Related papers
- Invar-RAG: Invariant LLM-aligned Retrieval for Better Generation [43.630437906898635]
We propose a novel two-stage fine-tuning architecture called Invar-RAG.
In the retrieval stage, an LLM-based retriever is constructed by integrating LoRA-based representation learning.
In the generation stage, a refined fine-tuning method is employed to improve LLM accuracy in generating answers based on retrieved information.
arXiv Detail & Related papers (2024-11-11T14:25:37Z) - An Early FIRST Reproduction and Improvements to Single-Token Decoding for Fast Listwise Reranking [50.81324768683995]
FIRST is a novel approach that integrates a learning-to-rank objective and leveraging the logits of only the first generated token.
We extend the evaluation of FIRST to the TREC Deep Learning datasets (DL19-22), validating its robustness across diverse domains.
Our experiments confirm that fast reranking with single-token logits does not compromise out-of-domain reranking quality.
arXiv Detail & Related papers (2024-11-08T12:08:17Z) - 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) - Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG [36.754491649652664]
Retrieval-augmented generation (RAG) empowers large language models (LLMs) to utilize external knowledge sources.
This paper investigates the detrimental impact of retrieved "hard negatives" as a key contributor.
To mitigate this and enhance the robustness of long-context LLM-based RAG, we propose both training-free and training-based approaches.
arXiv Detail & Related papers (2024-10-08T12:30:07Z) - Evaluating Generative Language Models in Information Extraction as Subjective Question Correction [49.729908337372436]
We propose a new evaluation method, SQC-Score.
Inspired by the principles in subjective question correction, we propose a new evaluation method, SQC-Score.
Results on three information extraction tasks show that SQC-Score is more preferred by human annotators than the baseline metrics.
arXiv Detail & Related papers (2024-04-04T15:36:53Z) - Make Large Language Model a Better Ranker [20.532118635672763]
This paper introduces the large language model framework with Aligned Listwise Ranking Objectives (ALRO)
ALRO is designed to bridge the gap between the capabilities of LLMs and nuanced requirements of ranking tasks.
Our evaluative studies reveal that ALRO outperforms both existing embedding-based recommendation methods and LLM-based recommendation baselines.
arXiv Detail & Related papers (2024-03-28T07:22:16Z) - 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) - Zero-Shot Listwise Document Reranking with a Large Language Model [58.64141622176841]
We propose Listwise Reranker with a Large Language Model (LRL), which achieves strong reranking effectiveness without using any task-specific training data.
Experiments on three TREC web search datasets demonstrate that LRL not only outperforms zero-shot pointwise methods when reranking first-stage retrieval results, but can also act as a final-stage reranker.
arXiv Detail & Related papers (2023-05-03T14:45:34Z)
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.