paper-with-me

Papers

Trustworthy Answers, Messier Data: Bridging the Gap in Low-Resource Retrieval-Augmented Generation for Domain Expert Systems

2025-02-26 · Nayoung Choi, Grace Byun, Andrew Chung, Ellie S. Paek, Shinsun Lee, Jinho D. Choi

RAG has become a key technique for enhancing LLMs by reducing hallucinations, especially in domain expert systems where LLMs may lack sufficient inherent knowledge. However, developing these systems in low-resource settings introduces several challenges: (1) handling heterogeneous data sources, (2) optimizing retrieval phase for trustworthy answers, and (3) evaluating generated answers across diverse aspects. To address these, we introduce a data generation pipeline that transforms raw multi-modal data into structured corpus and Q&A pairs, an advanced re-ranking phase improving retrieval precision, and a reference matching algorithm enhancing answer traceability. Applied to the automotive engineering domain, our system improves factual correctness (+1.94), informativeness (+1.16), and helpfulness (+1.67) over a non-RAG baseline, based on a 1-5 scale by an LLM judge. These results highlight the effectiveness of our approach across distinct aspects, with strong answer grounding and transparency.

📄 PDF Abstract BibTeX arXiv:2502.19596

Code (0)

등록된 구현이 없습니다.

Tasks

InformativenessRAGRe-RankingRetrievalRetrieval-augmented Generation

Similar Papers 제목 키워드 기반

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation

2026-07-28 · Stefan Krsteski, Charlotte Meyer, Guillaume Allegre, Tony O'Halloran 외 arxiv

Evaluating AI agents in interactive environments is hindered by fragmented tasks, scaffolds, verifiers, and scoring rules. Existing efforts focus on narrow settings, remain limited in scale, or require costly reruns, lea…

Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness

2024-09-01 · Senthil Kumar Jagatheesaperumal, Mohamed Rahouti, Ali Alfatemi, Nasir Ghani 외

Federated Learning (FL) represents a paradigm shift in machine learning, allowing collaborative model training while keeping data localized. This approach is particularly pertinent in the Industrial Internet of Things (I…

Decision MakingFederated Learning

Quarantine Deceiving Yelp's Users by Detecting Unreliable Rating Reviews

2020-04-21 · Viet Trinh, Vikrant More, Samira Zare, Sheideh Homayon

Online reviews have become a valuable and significant resource, for not only consumers but companies, in decision making. In the absence of a trusted system, highly popular and trustworthy internet users will be assumed …

Decision MakingSpam detection

CORE-GPT: Combining Open Access research and large language models for credible, trustworthy question answering

2023-07-06 · David Pride, Matteo Cancellieri, Petr Knoth

In this paper, we present CORE-GPT, a novel question-answering platform that combines GPT-based language models and more than 32 million full-text open access scientific articles from CORE. We first demonstrate that GPT3…

ArticlesQuestion Answering

From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned Learning

2026-04-13 · Chen Zhan, Xiaoyu Tan, Gengchen Ma, Yu-Jie Xiong 외 arxiv

The integration of Large Language Models (LLMs) into clinical decision support is critically obstructed by their opaque and often unreliable reasoning. In the high-stakes domain of healthcare, correct answers alone are i…

Reinforcement Learning