paper-with-me

Papers

Towards Faithful and Robust LLM Specialists for Evidence-Based Question-Answering

2024-02-13 · Tobias Schimanski, Jingwei Ni, Mathias Kraus, Elliott Ash, Markus Leippold

Advances towards more faithful and traceable answers of Large Language Models (LLMs) are crucial for various research and practical endeavors. One avenue in reaching this goal is basing the answers on reliable sources. However, this Evidence-Based QA has proven to work insufficiently with LLMs in terms of citing the correct sources (source quality) and truthfully representing the information within sources (answer attributability). In this work, we systematically investigate how to robustly fine-tune LLMs for better source quality and answer attributability. Specifically, we introduce a data generation pipeline with automated data quality filters, which can synthesize diversified high-quality training and testing data at scale. We further introduce four test sets to benchmark the robustness of fine-tuned specialist models. Extensive evaluation shows that fine-tuning on synthetic data improves performance on both in- and out-of-distribution. Furthermore, we show that data quality, which can be drastically improved by proposed quality filters, matters more than quantity in improving Evidence-Based QA.

📄 PDF Abstract BibTeX arXiv:2402.08277

Code (1)

EdisonNi-hku/Robust_Evidence_Based_QA 공식 구현 pytorch

Tasks

Question Answering

Similar Papers 제목 키워드 기반

Faithful Temporal Question Answering over Heterogeneous Sources

2024-02-23 · Zhen Jia, Philipp Christmann, Gerhard Weikum

Temporal question answering (QA) involves time constraints, with phrases such as "... in 2019" or "... before COVID". In the former, time is an explicit condition, in the latter it is implicit. State-of-the-art methods h…

Question Answering

Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering

2024-08-27 · Haowei Du, Huishuai Zhang, Dongyan Zhao

To address the hallucination in generative question answering (GQA) where the answer can not be derived from the document, we propose a novel evidence-enhanced triplet generation framework, EATQA, encouraging the model t…

Generative Question AnsweringHallucinationQuestion AnsweringTriplet

FARSIQA: Faithful and Advanced RAG System for Islamic Question Answering

2025-10-29 · Mohammad Aghajani Asl, Behrooz Minaei Bidgoli arxiv

The advent of Large Language Models (LLMs) has revolutionized Natural Language Processing, yet their application in high-stakes, specialized domains like religious question answering is hindered by challenges like halluc…

Question Answering

SQuAI: Scientific Question-Answering with Multi-Agent Retrieval-Augmented Generation

2025-10-17 · Ines Besrour, Jingbo He, Tobias Schreieder, Michael Färber arxiv

We present SQuAI (https://squai.scads.ai/), a scalable and trustworthy multi-agent retrieval-augmented generation (RAG) framework for scientific question answering (QA) with large language models (LLMs). SQuAI addresses …

Question Answering

Decomposing and Revising What Language Models Generate

2025-08-31 · Zhichao Yan, Jiaoyan Chen, Jiapu Wang, Xiaoli Li 외 arxiv

Attribution is crucial in question answering (QA) with Large Language Models (LLMs).SOTA question decomposition-based approaches use long form answers to generate questions for retrieving related documents. However, the …

Question Answering