Faithfulness in VLMs

VLM: Vision-Language Model

Overview

This field studies whether vision-language models use image or video evidence to make decisions, rather than relying on language priors or producing plausible but unsupported explanations. Researchers test this with counterfactual image edits, modality ablations, grounding and attribution measures, and benchmarks for hallucination, spatial reasoning, and evidence use. Methods include process-level supervision and grounding rewards, as well as inference-time decoding or causal interventions that strengthen visual evidence and suppress conflicting language pathways. A central challenge is that accurate answers and fluent reasoning do not prove faithful evidence use, while reducing hallucinations can also make responses less informative.

Latest papers

CardsList

92 papers12 papers in the last four weeks, down 20% on the four weeks before. 0.1% of all new papers.

  1. More Than Meets the Eye? Uncovering the Reasoning-Planning Disconnect in Training Vision-Language Driving Models

    Oct 6, 2025Xurui Song, Shuo Huai, JingJing Jiang +2VLMs for Autonomous DrivingReasoning for VLA Models

  2. TAR: Temporal Anchor-Constrained Reasoning for Video Temporal Grounding

    Aug 11, 2025Chaohong Guo, Xun Mo, Yongwei Nie +3Temporal Video GroundingVision-Language Models