paper-with-me

홈 › Papers

Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism

2024-02-20 · Hippolyte Gisserot-Boukhlef, Manuel Faysse, Emmanuel Malherbe, Céline Hudelot, Pierre Colombo

Neural Information Retrieval (NIR) has significantly improved upon heuristic-based Information Retrieval (IR) systems. Yet, failures remain frequent, the models used often being unable to retrieve documents relevant to the user's query. We address this challenge by proposing a lightweight abstention mechanism tailored for real-world constraints, with particular emphasis placed on the reranking phase. We introduce a protocol for evaluating abstention strategies in black-box scenarios (typically encountered when relying on API services), demonstrating their efficacy, and propose a simple yet effective data-driven mechanism. We provide open-source code for experiment replication and abstention implementation, fostering wider adoption and application in diverse contexts.

📄 PDF Abstract BibTeX arXiv:2402.12997

Code (2)

artefactory/abstention-reranker 공식 구현 pytorch
hgissbkh/abstention-reranker 공식 구현 pytorch

Tasks

Information RetrievalRerankingRetrieval

Similar Papers 제목 키워드 기반

Knowing When to Abstain: Medical LLMs Under Clinical Uncertainty

2026-01-18 · Sravanthi Machcha, Sushrita Yerra, Sahil Gupta, Aishwarya Sahoo 외 arxiv

Current evaluation of large language models (LLMs) overwhelmingly prioritizes accuracy; however, in real-world and safety-critical applications, the ability to abstain when uncertain is equally vital for trustworthy depl…

Question Answering

ReGAIN: Retrieval-Grounded AI Framework for Network Traffic Analysis

2025-12-23 · Shaghayegh Shajarian, Kennedy Marsh, James Benson, Sajad Khorsandroo 외 arxiv

Modern networks generate vast, heterogeneous traffic that must be continuously analyzed for security and performance. Traditional network traffic analysis systems, whether rule-based or machine learning-driven, often suf…

An Explainable Agentic AI Framework for Uncertainty-Aware and Abstention-Enabled Acute Ischemic Stroke Imaging Decisions

2026-01-03 · Md Rashadul Islam arxiv

Artificial intelligence models have shown strong potential in acute ischemic stroke imaging, particularly for lesion detection and segmentation using computed tomography and magnetic resonance imaging. However, most exis…

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation

2024-06-19 · Di wu, Jia-Chen Gu, Fan Yin, Nanyun Peng 외

Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. However, there are significant trustworthiness concerns as RALMs are prone to generating unfa…

RerankingRetrievalRetrieval-augmented GenerationUncertainty Quantification

R2-KG: General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs

2025-02-18 · Sumin Jo, Junseong Choi, Jiho Kim, Edward Choi

Recent studies have combined Large Language Models (LLMs) with Knowledge Graphs (KGs) to enhance reasoning, improving inference accuracy without additional training while mitigating hallucination. However, existing frame…

HallucinationKnowledge Graphs