11 papers
Attention-Guided Saliency Maps for Interpreting Visualization Literacy in VLMs
Maeve Hutchinson, Abderrahmane Wassim Mehdaoui, Pranava Madhyastha
Understanding how vision-language models (VLMs) interpret data visualizations remains an open problem, and is increasingly important as these models are used for analytical tasks w…
DecompSR: A dataset for decomposed analyses of compositional multihop spatial reasoning
Lachlan McPheat, Navdeep Kaur, Robert Blackwell +3
We introduce DecompSR, decomposed spatial reasoning, a large benchmark dataset (over 5m datapoints) and generation framework designed to analyse compositional spatial reasoning abi…
A Cognitively Grounded Bayesian Framework for Misinformation Susceptibility
Pranava Madhyastha
In this (work in progress) paper, we present Bounded Pragmatic Listener (or BPL), a cognitively grounded Bayesian framework for modelling susceptibility to information disorder. BP…
Working Memory Constraints Scaffold Learning in Transformers under Data Scarcity
Pranava Madhyastha, Dagmar Adamcova
We investigate the integration of human-like working memory constraints into the Transformer architecture and implement several cognitively inspired attention variants, including f…
Learning and Enforcing Context-Sensitive Control for LLMs
Mohammad Albinhassan, Pranava Madhyastha, Mark Law +1
Controlling the output of Large Language Models (LLMs) through context-sensitive constraints has emerged as a promising approach to overcome the limitations of Context-Free Grammar…
: Semantically Controlled Decoding
Mohammad Albinhassan, Pranava Madhyastha, Alessandra Russo
Ensuring both syntactic and semantic correctness in Large Language Model (LLM) outputs remains a significant challenge, despite being critical for real-world deployment. In this pa…