paper-with-me

Papers

Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversational Search

2024-02-19 · Chanwoong Yoon, Gangwoo Kim, Byeongguk Jeon, Sungdong Kim, Yohan Jo, Jaewoo Kang

Conversational search, unlike single-turn retrieval tasks, requires understanding the current question within a dialogue context. The common approach of rewrite-then-retrieve aims to decontextualize questions to be self-sufficient for off-the-shelf retrievers, but most existing methods produce sub-optimal query rewrites due to the limited ability to incorporate signals from the retrieval results. To overcome this limitation, we present a novel framework RetPO (Retriever's Preference Optimization), which is designed to optimize a language model (LM) for reformulating search queries in line with the preferences of the target retrieval systems. The process begins by prompting a large LM to produce various potential rewrites and then collects retrieval performance for these rewrites as the retrievers' preferences. Through the process, we construct a large-scale dataset called RF collection, containing Retrievers' Feedback on over 410K query rewrites across 12K conversations. Furthermore, we fine-tune a smaller LM using this dataset to align it with the retrievers' preferences as feedback. The resulting model achieves state-of-the-art performance on two recent conversational search benchmarks, significantly outperforming existing baselines, including GPT-3.5.

📄 PDF Abstract BibTeX arXiv:2402.11827

Code (0)

등록된 구현이 없습니다.

Tasks

Conversational SearchLanguage ModelingLanguage ModellingRetrieval

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Adam 설명 없음

Similar Papers 제목 키워드 기반

A Multimodal Dense Retrieval Approach for Speech-Based Open-Domain Question Answering

2024-09-20 · Georgios Sidiropoulos, Evangelos Kanoulas

Speech-based open-domain question answering (QA over a large corpus of text passages with spoken questions) has emerged as an important task due to the increasing number of users interacting with QA systems via speech in…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Open-Domain Question AnsweringPassage Retrieval+4

Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation

2024-11-06 · Yuhang Liu, Xueyu Hu, Shengyu Zhang, Jingyuan Chen 외

Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs). Previous approaches typically train retrievers based on semantic sim…

HallucinationRAGRetrievalRetrieval-augmented Generation+2

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation

2025-02-10 · Guoxin Chen, Minpeng Liao, Peiying Yu, Dingmin Wang 외

Retrieval-augmented generation (RAG) systems face a fundamental challenge in aligning independently developed retrievers and large language models (LLMs). Existing approaches typically involve modifying either component …

RAGRetrievalRetrieval-augmented Generation

Retriever Portfolios: A Principled Approach to Adaptive RAG

2026-05-29 · Miltiadis Stouras, Vincent Cohen-Addad, Silvio Lattanzi, Ola Svensson arxiv

Retrieval-augmented generation (RAG) systems typically rely on a single retriever and a single set of hyperparameters, despite facing highly heterogeneous queries that range from simple factoid questions to complex multi…

Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers

2024-06-16 · Tianhua Zhang, Kun Li, Hongyin Luo, Xixin Wu 외

Query rewriting is a crucial technique for passage retrieval in open-domain conversational question answering (CQA). It decontexualizes conversational queries into self-contained questions suitable for off-the-shelf retr…

Conversational Question AnsweringPassage RetrievalQuestion AnsweringRetrieval