Detecting Token-Level Hallucinations Using Variance Signals: A Reference-Free Approach
Large Language Models (LLMs) have demonstrated impressive generative capabilities across diverse tasks but remain susceptible to hallucinations, confidently generated yet factually incorrect outputs. We introduce a reference-free, token-level hallucination detection framework that leverages the variance in token log-probabilities across multiple stochastic generations. Unlike prior methods that require ground-truth references or sentence-level verification, our approach is model-agnostic, interpretable, and suited for real-time or post-hoc analysis. We evaluate our method on unanswerable question prompts from the SQuAD v2 dataset and benchmark across three autoregressive models of varying scales: GPT-Neo 125M, Falcon 1B, and Mistral 7B. Through both quantitative metrics and visual diagnostics, we show that token-level variance reliably highlights instability in model outputs and correlates with hallucination patterns. Our framework is lightweight, reproducible, and adaptable to multiple domains, offering a valuable diagnostic tool for analyzing generative reliability in LLMs.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Grounding or Guessing? Visual Signals for Detecting Hallucinations in Sign Language Translation
Hallucination, where models generate fluent text unsupported by visual evidence, remains a major flaw in vision-language models and is particularly critical in sign language translation (SLT). In SLT, meaning depends on …
Sign Language Translationmultimodal generationVisual GroundingMetaToken: Detecting Hallucination in Image Descriptions by Meta Classification
Large Vision Language Models (LVLMs) have shown remarkable capabilities in multimodal tasks like visual question answering or image captioning. However, inconsistencies between the visual information and the generated te…
HallucinationImage CaptioningQuestion AnsweringSentence+1Detecting Hallucinations in Retrieval-Augmented Generation via Semantic-level Internal Reasoning Graph
The Retrieval-augmented generation (RAG) system based on Large language model (LLM) has made significant progress. It can effectively reduce factuality hallucinations, but faithfulness hallucinations still exist. Previou…
ESREAL: Exploiting Semantic Reconstruction to Mitigate Hallucinations in Vision-Language Models
Hallucinations in vision-language models pose a significant challenge to their reliability, particularly in the generation of long captions. Current methods fall short of accurately identifying and mitigating these hallu…
HallucinationSemantic SimilaritySemantic Textual SimilarityTheory of Hallucinations based on Equivariance
This study aims to acquire knowledge for creating very large language models that are immune to hallucinations. Hallucinations in contemporary large language models are often attributed to a misunderstanding of real-worl…
Hallucination