Published in Conference on Language Modeling 2026, 2026
This paper investigates popular claims of introspection and argues that they don’t pass necessity criteria of privileged access.
Authors: Singh, S., Lizen, T., Ravfogel, S.(2026)
Download Paper
Published in UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models (NeurIPS workshop 2024), 2024
Humans process text visually; our work studies the semantics of text rendered in images. We show that the semantic information captured by image representations can decisively classify the sentiment of sentences and is robust against visual attributes like font and not based on simple character frequency associations.
Authors: Sreeram Vennam*, Shashwat Singh*, Anirudh Govil, Ponnurangam Kumaraguru
Download Paper
Published in The Forty-first International Conference on Machine Learning, 2024
This paper investigates the formal and empirical properties of steering functions, i.e., transformation of the neural language model’s representations that alter its behavior.
Authors: Singh, S.∗, Ravfogel, S.∗, Herzig, J., Aharoni, R., Cotterell, R., Kumaraguru, P. (2024)
Download Paper
Published in The 8th Workshop on Representation Learning for NLP (RepL4NLP). 61st Annual Meeting of the Association for Computational Linguistics (ACL), 2023
We hypothesize about why pretrained LMs are inconsistent under negation: when the statement could refer to multiple ground entities with conflicting properties, negation may not entail a change in output. This means negation minimal pairs in different training samples can have the same completion in pretraining corpora.
Authors: Shashwat Singh*, Shashwat Goel*, Saujas Vaduguru, Ponnurangam Kumaraguru
Download Paper