ASRank: Zero-Shot Re-Ranking with Answer Scent for Document Retrieval (2025.findings-naacl)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation models fail to rank the most relevant documents at the top . conventional retrieval methods fail to find the most important documents . |
| Approach: | They propose a new method for scoring retrieved documents using zero-shot answer scent based on a pre-trained large language model to compute the likelihood of document-derived answers aligning with the answer scent. |
| Outcome: | The proposed method improves top-1 retrieval accuracy on NQ, TriviaQA, WebQA, ArchivalQA, HotpotQA, and Entity Questions. |
Similar Papers
InfoGain-RAG: Boosting Retrieval-Augmented Generation through Document Information Gain-based Reranking and Filtering (2025.emnlp-main)
Copied to clipboard
Zihan Wang, Zihan Liang, Zhou Shao, Yufei Ma, Huangyu Dai, Ben Chen, Lingtao Mao, Chenyi Lei, Yuqing Ding, Han Li
| Challenge: | Retrieval-Augmented Generation (RAG) frameworks struggle with identifying whether retrieved documents meaningfully contribute to answer generation. |
| Approach: | They propose a document-related metric to quantify the contribution of retrieved documents to correct answer generation. |
| Outcome: | The proposed framework outperforms existing approaches on both single and multiple retrieval paradigms. |
Improving Passage Retrieval with Zero-Shot Question Generation (2022.emnlp-main)
Copied to clipboard
Devendra Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan, Wen-tau Yih, Joelle Pineau, Luke Zettlemoyer
| Challenge: | Existing re-ranking methods for open-domain question answering are not domain- or task-specific. |
| Approach: | They propose a simple and effective re-ranking method for improving passage retrieval in open-domain question answering. |
| Outcome: | The proposed method outperforms strong supervised models on open-domain questions and triviaQA datasets on top-1000 passages. |
GENRA: Enhancing Zero-shot Retrieval with Rank Aggregation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have been shown to perform zero-shot document retrieval, a process that typically consists of two steps: retrieving relevant documents, and re-ranking them based on their relevance to the query. |
| Approach: | They propose a new approach to zero-shot document retrieval that incorporates rank aggregation to improve retrieval effectiveness. |
| Outcome: | The proposed approach improves existing methods on benchmark datasets and shows that it can perform zero-shot retrieval. |
Question Decomposition for Retrieval-Augmented Generation (2025.acl-srw)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) is effective for question answering tasks . multi-hop questions, such as "Which company among NVIDIA, Apple, and Google made the biggest profit in 2023?" challenge RAG because relevant facts are often distributed across multiple documents . |
| Approach: | They propose a pipeline that incorporates question decomposition to ground large language models in verifiable external sources. |
| Outcome: | The proposed approach improves retrieval and answer accuracy over standard RAG . multi-hop questions often require multiple documents to support the model . |
RaFe: Ranking Feedback Improves Query Rewriting for RAG (2024.findings-emnlp)
Copied to clipboard
Shengyu Mao, Yong Jiang, Boli Chen, Xiao Li, Peng Wang, Xinyu Wang, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang
| Challenge: | Large Language Models (LLMs) and Retrieval Augmentation Generation (RAG) techniques have evolved to enhance document retrieval by reformulating queries. |
| Approach: | They propose a framework for training query rewriting models that leverages a reranker framework. |
| Outcome: | The proposed framework provides ranking feedback aligned well with the rewriting objectives without needing signals from annotations and supports both online and offline training models. |
RE-RAG: Improving Open-Domain QA Performance and Interpretability with Relevance Estimator in Retrieval-Augmented Generation (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to retrieval augmented generation (RAG) are based on parametric knowledge and external knowledge. |
| Approach: | They propose a weakly supervised method for training a relevance estimator (RE) that provides relative relevance between contexts as previous rerankers did, and provides confidence, which can be used to classify whether given context is useful for answering the given question. |
| Outcome: | The proposed framework improves previously unreferenced large language models and can be trained with a small generator without labels for correct contexts. |
Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing efforts to estimate document utility rely on downstream generation performance, which conflates the influence of external documents with the intrinsic knowledge of the LLM. |
| Approach: | They propose an uplift-based definition of document utility that quantifies each document’s marginal benefit over the LLM’s internal knowledge. |
| Outcome: | The proposed framework improves the performance of the LLM by incorporating external retrieved documents into the model. |
Test-time Corpus Feedback: From Retrieval to RAG (2026.findings-eacl)
Copied to clipboard
| Challenge: | Retrieval-augmented generation (RAG) pipelines treat retrieval and reasoning as isolated components, limiting performance on complex tasks. |
| Approach: | They propose to integrate large language models with retrieval to improve query quality . they also propose to use feedback to improve the query, retrieved context, or document pool . |
| Outcome: | The proposed methods bridge IR and NLP perspectives and highlight retrieval as a dynamic, learnable component of end-to-end RAG systems. |
MrRank: Improving Question Answering Retrieval System through Multi-Result Ranking Model (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing IR techniques contain deficiencies, posing a performance bottleneck . combining diverse approaches to retrieve information is a viable strategy . |
| Approach: | They propose an approach that leverages learning-to-rank techniques to combine heterogeneous IR systems. |
| Outcome: | The proposed method outperforms existing methods on two Retrieval Question Answering tasks. |
ListT5: Listwise Reranking with Fusion-in-Decoder Improves Zero-shot Retrieval (2024.acl-long)
Copied to clipboard
| Challenge: | Existing listwise reranking models rely on pointwise sizing of each passage . Until now, listwise models lack the ability to compare between passages at inference time . |
| Approach: | They propose a listwise reranking approach based on Fusion-in-Decoder that handles multiple candidate passages at train and inference time. |
| Outcome: | The proposed model outperforms the state-of-the-art RankT5 model on the BEIR benchmark for zero-shot retrieval task with a notable +1.3 gain in the average NDCG@10 score. |