paper-with-me

Papers

Evidence Selection as a Token-Level Prediction Task

2021-11-01 · EMNLP (FEVER) 2021 11 · Dominik Stammbach

In Automated Claim Verification, we retrieve evidence from a knowledge base to determine the veracity of a claim. Intuitively, the retrieval of the correct evidence plays a crucial role in this process. Often, evidence selection is tackled as a pairwise sentence classification task, i.e., we train a model to predict for each sentence individually whether it is evidence for a claim. In this work, we fine-tune document level transformers to extract all evidence from a Wikipedia document at once. We show that this approach performs better than a comparable model classifying sentences individually on all relevant evidence selection metrics in FEVER. Our complete pipeline building on this evidence selection procedure produces a new state-of-the-art result on FEVER, a popular claim verification benchmark.

📄 PDF Abstract BibTeX

Code (1)

dominiksinsaarland/document-level-fever 공식 구현 pytorch

Tasks

Claim VerificationEvidence SelectionPredictionRetrievalSentenceSentence Classification

Similar Papers 제목 키워드 기반

Inferring from Logits: Exploring Best Practices for Decoding-Free Generative Candidate Selection

2025-01-28 · Mingyu Derek Ma, Yanna Ding, Zijie Huang, Jianxi Gao 외

Generative Language Models rely on autoregressive decoding to produce the output sequence token by token. Many tasks such as preference optimization, require the model to produce task-level output consisting of multiple …

Multiple-choice

ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair

2026-07-02 · Chiwang Luk, Matin Mohammad Najafi, Zhifeng Jia, Wei Yang 외 arxiv

Large language model agents can repair real repository issues, but they often spend large context budgets on whole-file reads, broad searches, and long terminal outputs where useful evidence is mixed with irrelevant code…

Program Repair

Selective State-Space Adaptation and Retrieval for Language Model Reasoning

2026-07-21 · Atahan Dokme, Larry Heck arxiv

Low-rank adaptation introduces a static learned update applied identically to every input. The update provides task-level adaptation but does not explicitly represent token-level or instance-level state variation. A fami…

SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction

2026-06-03 · Kenfeng Huang, Yi Cai, Xin Wu, Zikun Deng 외 arxiv

Zero-shot information extraction (IE) with large language models (LLMs) has attracted increasing attention due to its flexibility in adapting to new schemas and domains without task-specific training. Existing approaches…

Information Extraction

AdaGATE: Adaptive Gap-Aware Token-Efficient Evidence Assembly for Multi-Hop Retrieval-Augmented Generation

2026-05-04 · Yilin Guo, Yinshan Wang, Yixuan Wang arxiv

Retrieval-augmented generation (RAG) remains brittle on multi-hop questions in realistic deployment settings, where retrieved evidence may be noisy or redundant and only limited context can be passed to the generator. Ex…