Back to search

Institutional Repository of Vilnius University

Analysis of algorithms to reduce hallucinations in vision language models /

Abstract

dc:description

Vision-Language Models (VLMs) exhibit impressive multimodal capabilities but remain susceptible to hallucinations — fluent yet visually ungrounded or factually incorrect outputs. This thesis analyzes a white-box hallucination detection framework, Multi-Token Reliability Estimation (MTRE), applied to the LLaVA-v1.5-7B architecture, which exploits internal logit dynamics to detect unreliability during generation. Experiments were conducted on the MAD-Bench and POPE benchmarks, investigating the impact of hyperparameters: generation temperature and the token logit sequence length. Results show that in-domain performance peaks at an ultra-narrow window of 2 logits (AUROC of 97.67%), improves substantially as the sequence is expanded to 20 logits. Simultaneous cross-dataset and cross-prompt transfer causes complete classifier collapse. High decoding temperatures introduce arithmetic overflow that is recoverable via sanitization, though boundary calibration remains limited under small training sets. The findings suggest that effective hallucination detection benefits from wider token horizons and is highly sensitive to both prompt format and dataset shifts.

Degree

thesis:*
Grantor dc:publisher
Institutional Repository of Vilnius University
Year dc:date
2026

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Bruškytė, Brigita,

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • info:eu-repo/semantics/openAccess
Language dc:language
eng

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Vilnius University
Base URL
epublications.vu.lt/oai
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Bruškytė, Brigita,. Analysis of algorithms to reduce hallucinations in vision language models /. Institutional Repository of Vilnius University, 2026. https://repository.vu.lt/VU:ELABAETD308332492&prefLang=en_US