paper-with-me

홈 › Papers

Proximity-Based Evidence Retrieval for Uncertainty-Aware Neural Networks

2025-09-11 · Hassan Gharoun, Mohammad Sadegh Khorshidi, Kasra Ranjbarigderi, Fang Chen, Amir H. Gandomi arxiv

This work proposes an evidence-retrieval mechanism for uncertainty-aware decision-making that replaces a single global cutoff with an evidence-conditioned, instance-adaptive criterion. For each test instance, proximal exemplars are retrieved in an embedding space; their predictive distributions are fused via Dempster-Shafer theory. The resulting fused belief acts as a per-instance thresholding mechanism. Because the supporting evidences are explicit, decisions are transparent and auditable. Experiments on CIFAR-10/100 with BiT and ViT backbones show higher or comparable uncertainty-aware performance with materially fewer confidently incorrect outcomes and a sustainable review load compared with applying threshold on prediction entropy. Notably, only a few evidences are sufficient to realize these gains; increasing the evidence set yields only modest changes. These results indicate that evidence-conditioned tagging provides a more reliable and interpretable alternative to fixed prediction entropy thresholds for operational uncertainty-aware decision-making.

📄 PDF Abstract BibTeX arXiv:2509.13338

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Beyond "What to Retrieve": Uncertainty in Retrieval-Augmented Code Generation

2026-07-27 · Chandan Kumar Sah, Li Zhang, Xiaoli Lian arxiv

Repository-level code generation relies on heterogeneous evidence whose relevance, compatibility, and completeness are inherently uncertain. Similar-code examples, repository context, and project-specific APIs may provid…

Code Generation

Uncertainty-Aware Hybrid Retrieval for Long-Document RAG

2026-06-11 · Hoin Jung, Xiaoqian Wang arxiv

Retrieval augmented generation (RAG) depends critically on the quality and granularity of retrieved evidence. Large retrieval units preserve context but often introduce irrelevant content, which can dilute answer bearing…

Question Answering

BELIEF: Structured Evidence Modeling and Uncertainty-Aware Fusion for Biomedical Question Answering

2026-05-17 · Chang Zong, Hao Ning, Siliang Tang, Jie Huang 외 arxiv

Biomedical question answering often requires decisions from retrieved literature whose relevance, quality, and support for candidate answers are uneven. Most retrieval-augmented large language model (LLM) methods feed th…

Question Answering

EvidentialRAG: Quantifying and Mitigating Information Conflict in Multi-Source Retrieval-Augmented Generation via Evidential Deep Learning

2026-07-11 · S M Asif Hossain, Ruksat Khan Shayoni, M. F. Mridha arxiv

Retrieval-augmented generation grounds large language models in external evidence, but most pipelines still treat retrieved passages as deterministic and mutually consistent context. In open information environments, ret…

Question Answering

Entropic Claim Resolution: Uncertainty-Driven Evidence Selection for RAG

2026-03-30 · Davide Di Gioia arxiv

Current Retrieval-Augmented Generation (RAG) systems predominantly rely on relevance-based dense retrieval, sequentially fetching documents to maximize semantic similarity with the query. However, in knowledge-intensive …

Semantic Similarity