VLMs show answer inertia in CoT reasoning and remain influenced by misleading textual cues even with sufficient visual evidence, making CoT an incomplete window into modality reliance.
Are self-explanations from large language models faithful? In Findings of the Association for Computational Linguistics: ACL 2024, pp.\ 295--337, Bangkok, Thailand, August 2024
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
iPOE derives and optimizes guidelines from explanations to create interpretable prompts, yielding up to 31% and 35% gains over standard and random-guideline prompts on four datasets.
citing papers explorer
-
Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models
VLMs show answer inertia in CoT reasoning and remain influenced by misleading textual cues even with sufficient visual evidence, making CoT an incomplete window into modality reliance.
-
iPOE: Interpretable Prompt Optimization via Explanations
iPOE derives and optimizes guidelines from explanations to create interpretable prompts, yielding up to 31% and 35% gains over standard and random-guideline prompts on four datasets.