paper-with-me

Papers

Zero-Shot Multi-task Hallucination Detection

2024-03-18 · Patanjali Bhamidipati, Advaith Malladi, Manish Shrivastava, Radhika Mamidi

In recent studies, the extensive utilization of large language models has underscored the importance of robust evaluation methodologies for assessing text generation quality and relevance to specific tasks. This has revealed a prevalent issue known as hallucination, an emergent condition in the model where generated text lacks faithfulness to the source and deviates from the evaluation criteria. In this study, we formally define hallucination and propose a framework for its quantitative detection in a zero-shot setting, leveraging our definition and the assumption that model outputs entail task and sample specific inputs. In detecting hallucinations, our solution achieves an accuracy of 0.78 in a model-aware setting and 0.61 in a model-agnostic setting. Notably, our solution maintains computational efficiency, requiring far less computational resources than other SOTA approaches, aligning with the trend towards lightweight and compressed models.

📄 PDF Abstract BibTeX arXiv:2403.12244

Code (0)

등록된 구현이 없습니다.

Tasks

Computational EfficiencyHallucinationText Generation

Similar Papers 제목 키워드 기반

LLM Hallucination Reasoning with Zero-shot Knowledge Test

2024-11-14 · Seongmin Lee, Hsiang Hsu, Chun-Fu Chen

LLM hallucination, where LLMs occasionally generate unfaithful text, poses significant challenges for their practical applications. Most existing detection methods rely on external knowledge, LLM fine-tuning, or hallucin…

Hallucination

Attention-guided Self-reflection for Zero-shot Hallucination Detection in Large Language Models

2025-01-17 · Qiang Liu, Xinlong Chen, Yue Ding, Shizhen Xu 외

Hallucination has emerged as a significant barrier to the effective application of Large Language Models (LLMs). In this work, we introduce a novel Attention-Guided SElf-Reflection (AGSER) approach for zero-shot hallucin…

Hallucination

UniFa: A unified feature hallucination framework for any-shot object detection

2025-03-01 · journal 2025 3 · Hui Nie, Ruiping Wang, Xilin Chen

Any-shot object detection seeks to simultaneously detect base (many-shot), few-shot and zero-shot categories. The primary challenge lies in insufficient visual data for rare (few-shot and zero-shot) categories, hindering…

Generalized Zero-Shot Object DetectionHallucinationobject-detectionObject Detection+1

Lowest Span Confidence: A Zero-Shot Metric for Efficient and Black-Box Hallucination Detection in LLMs

2026-01-07 · Yitong Qiao, Licheng Pan, Yu Mi, Lei Liu 외 arxiv

Hallucinations in Large Language Models (LLMs), i.e., the tendency to generate plausible but non-factual content, pose a significant challenge for their reliable deployment in high-stakes environments. However, existing …

"AGI" team at SHROOM-CAP: Data-Centric Approach to Multilingual Hallucination Detection using XLM-RoBERTa

2025-11-23 · Harsh Rathva, Pruthwik Mishra, Shrikant Malviya arxiv

The detection of hallucinations in multilingual scientific text generated by Large Language Models (LLMs) presents significant challenges for reliable AI systems. This paper describes our submission to the SHROOM-CAP 202…