paper-with-me

홈 › Papers

LoRE: Logit-Ranked Retriever Ensemble for Enhancing Open-Domain Question Answering

2024-10-13 · Saikrishna Sanniboina, Shiv Trivedi, Sreenidhi Vijayaraghavan

Retrieval-based question answering systems often suffer from positional bias, leading to suboptimal answer generation. We propose LoRE (Logit-Ranked Retriever Ensemble), a novel approach that improves answer accuracy and relevance by mitigating positional bias. LoRE employs an ensemble of diverse retrievers, such as BM25 and sentence transformers with FAISS indexing. A key innovation is a logit-based answer ranking algorithm that combines the logit scores from a large language model (LLM), with the retrieval ranks of the passages. Experimental results on NarrativeQA, SQuAD demonstrate that LoRE significantly outperforms existing retrieval-based methods in terms of exact match and F1 scores. On SQuAD, LoRE achieves 14.5\%, 22.83\%, and 14.95\% improvements over the baselines for ROUGE-L, EM, and F1, respectively. Qualitatively, LoRE generates more relevant and accurate answers, especially for complex queries.

📄 PDF Abstract BibTeX arXiv:2410.10042

Code (0)

등록된 구현이 없습니다.

Tasks

Answer GenerationLanguage ModelingLanguage ModellingLarge Language ModelOpen-Domain Question AnsweringQuestion AnsweringRetrievalSentence

Similar Papers 제목 키워드 기반

SWAP: Exploiting Second-Ranked Logits for Adversarial Attacks on Time Series

2023-09-06 · Chang George Dong, Liangwei Nathan Zheng, Weitong Chen, Wei Emma Zhang 외

Time series classification (TSC) has emerged as a critical task in various domains, and deep neural models have shown superior performance in TSC tasks. However, these models are vulnerable to adversarial attacks, where …

Time SeriesTime Series Classification

Hybrid and Collaborative Passage Reranking

2023-05-16 · Zongmeng Zhang, Wengang Zhou, Jiaxin Shi, Houqiang Li

In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between que…

Passage RerankingPassage RetrievalRerankingRetrieval

Exp4Fuse: A Rank Fusion Framework for Enhanced Sparse Retrieval using Large Language Model-based Query Expansion

2025-06-05 · Lingyuan Liu, Mengxiang Zhang

Large Language Models (LLMs) have shown potential in generating hypothetical documents for query expansion, thereby enhancing information retrieval performance. However, the efficacy of this method is highly dependent on…

Information RetrievalLanguage ModelingLanguage ModellingLarge Language Model+1

Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models

2023-11-28 · Zhihe Lu, Jiawang Bai, Xin Li, Zeyu Xiao 외

Fine-tuning pre-trained vision-language models (VLMs), e.g., CLIP, for the open-world generalization has gained increasing popularity due to its practical value. However, performance advancements are limited when relying…

Prompt Engineering

Quantifying Retriever-Generator Alignment in RAG with Local Explanations

2026-01-29 · Korbinian Randl, Guido Rocchietti, Aron Henriksson, Ziawasch Abedjan 외 arxiv

Retrieval-Augmented Generation (RAG) systems combine dense retrievers and language models to ground their outputs in external documents. However, the interaction between these components remains opaque, creating challeng…