English
Related papers

Related papers: Claim-Selective Certification for High-Risk Medica…

200 papers

Standard Retrieval-Augmented Generation (RAG) systems predominantly rely on semantic relevance as a proxy for utility. However, this assumption collapses in realistic decision-making scenarios where user queries are laden with cognitive…

Computation and Language · Computer Science 2026-05-05 Peiyang Liu , Qiang Yan , Ziqiang Cui , Di Liang , Xi Wang , Wei Ye

Building reliable retrieval-augmented generation (RAG) systems requires more than adding powerful components; it requires understanding how they interact. Using ablation studies on 50 queries (15 answerable, 10 edge cases, and 25…

Computation and Language · Computer Science 2025-12-01 Jithin Krishnan

When evaluating the performance of clinical machine learning models, one must consider the deployment population. When the population of patients with observed labels is only a subset of the deployment population (label selection), standard…

Machine Learning · Computer Science 2022-09-20 Conor K. Corbin , Michael Baiocchi , Jonathan H. Chen

Evaluating clustering quality with reliable evaluation metrics like normalized mutual information (NMI) requires labeled data that can be expensive to annotate. We focus on the underexplored problem of estimating clustering quality with…

Machine Learning · Computer Science 2022-10-04 Nihal V. Nayak , Ethan R. Elenberg , Clemens Rosenbaum

Patch robustness certification is an emerging verification approach for defending against adversarial patch attacks with provable guarantees for deep learning systems. Certified recovery techniques guarantee the prediction of the sole true…

Machine Learning · Computer Science 2025-08-01 Qilin Zhou , Haipeng Wang , Zhengyuan Wei , W. K. Chan

Retrieval-Augmented Generation (RAG) is an effective approach to enhance the factual accuracy of large language models (LLMs) by retrieving information from external databases, which are typically composed of diverse sources, to supplement…

Machine Learning · Computer Science 2025-10-15 Jeongyeon Hwang , Junyoung Park , Hyejin Park , Dongwoo Kim , Sangdon Park , Jungseul Ok

Retrieval-Augmented Generation (RAG) grounds language models in factual evidence but introduces critical challenges regarding knowledge conflicts between internalized parameters and retrieved information. However, existing reliability…

Information Retrieval · Computer Science 2026-04-24 Sunguk Shin , Meeyoung Cha , Byung-Jun Lee , Sungwon Park

Retrieval-augmented generation (RAG) has emerged as a promising approach to enhance the performance of large language models (LLMs) in knowledge-intensive tasks such as those from medical domain. However, the sensitive nature of the medical…

Computation and Language · Computer Science 2024-11-15 Nghia Trung Ngo , Chien Van Nguyen , Franck Dernoncourt , Thien Huu Nguyen

Large language models (LLMs) inevitably exhibit hallucinations since the accuracy of generated texts cannot be secured solely by the parametric knowledge they encapsulate. Although retrieval-augmented generation (RAG) is a practicable…

Computation and Language · Computer Science 2024-10-08 Shi-Qi Yan , Jia-Chen Gu , Yun Zhu , Zhen-Hua Ling

Retrieval-Augmented Generation (RAG) has emerged as a widely adopted approach for enhancing LLMs in scenarios that demand extensive factual knowledge. However, current RAG evaluations concentrate primarily on correctness, which may not…

Computation and Language · Computer Science 2026-03-23 Vinh Nguyen , Cuong Dang , Jiahao Zhang , Hoa Tran , Minh Tran , Trinh Chau , Thai Le , Lu Cheng , Suhang Wang

The goal of positive-unlabeled (PU) learning is to train a binary classifier on the basis of training data containing positive and unlabeled instances, where unlabeled observations can belong either to the positive class or to the negative…

Machine Learning · Statistics 2024-04-02 Paweł Teisseyre , Konrad Furmańczyk , Jan Mielniczuk

Scientific claim verification, the task of determining whether claims are entailed by scientific evidence, is fundamental to establishing discoveries in evidence while preventing misinformation. This process involves evaluating each…

Computation and Language · Computer Science 2026-04-14 Muxin Liu , Delip Rao , Grace Kim , Chris Callison-Burch

Retrieval-augmented reasoning (RAR) is a recent evolution of retrieval-augmented generation (RAG) that employs multiple reasoning steps for retrieval and generation. While effective for some complex queries, RAR remains vulnerable to errors…

Information Retrieval · Computer Science 2026-05-28 Heydar Soudani , Hamed Zamani , Faegheh Hasibi

Access to the right evidence does not guarantee that large language models (LLMs) will reason with it correctly. This gap between retrieval and reasoning is especially concerning in clinical settings, where outputs must align with…

Artificial Intelligence · Computer Science 2025-11-21 Deepthi Potluri , Aby Mammen Mathew , Jeffrey B DeWitt , Alexander L. Rasgon , Yide Hao , Junyuan Hong , Ying Ding

Cross-slice attack attribution in 6G networks requires identifying causal propagation chains through shared infrastructure in under 100 ms. Existing methods struggle to satisfy this strict SLA without sacrificing accuracy, because shared…

Cryptography and Security · Computer Science 2026-05-27 Minh K. Quan , Pubudu N. Pathirana

Multimodal agents increasingly choose tool calls from screenshots, documents, and webpages, where a false perceptual claim can turn hallucination from an answer-quality error into an authorization failure. We formalize this failure mode as…

Artificial Intelligence · Computer Science 2026-05-22 Guijia Zhang , Hao Zheng , Harry Yang

Retrieval-Augmented Generation (RAG) systems implicitly assume mutual consistency among retrieved documents -- an assumption that frequently fails in practice. We present ConflictRAG, a conflict-aware RAG framework that detects, classifies,…

Computation and Language · Computer Science 2026-05-19 Chenyu Wang , Yingmin Liu , Yang Shu

AI coding scaffolds like Claude Code and Codex use retrying: blocking actions flagged as risky and continuing the trajectory. We study retrying from an AI control perspective, which treats the model as potentially adversarial. We find that…

Artificial Intelligence · Computer Science 2026-05-27 James Lucassen , Adam Kaufman

Contrastive representation learning is a modern paradigm for learning representations of unlabeled data via augmentations -- precisely, contrastive models learn to embed semantically similar pairs of samples (positive pairs) closer than…

Machine Learning · Statistics 2026-01-01 Anna Van Elst , Debarghya Ghoshdastidar

This paper addresses the issues of insufficient coverage, unstable results, and limited reliability in retrieval-augmented generation under complex knowledge environments, and proposes a confidence control method that integrates…

Computation and Language · Computer Science 2025-11-03 Xiaofan Guo , Yaxuan Luan , Yue Kang , Xiangchen Song , Jinxu Guo