Publications

You can also find my articles on my Google Scholar profile.

Strong hallucinations from negation and how to fix them

Published in Findings of ACL 2024, 2024

Despite great performance on many tasks, language models (LMs) still struggle with reasoning, sometimes providing responses that cannot possibly be true because they stem from logical incoherence. We call such responses strong hallucinations and prove that they follow from its computation of its internal representations for logical operators and outputs from those representations Read more

Recommended citation: Asher, Nicholas, and Swarnadeep Bhar. "Strong hallucinations from negation and how to fix them." arXiv preprint arXiv:2402.10543 (2024).

Analyzing semantic faithfulness of language models via input intervention on conversational question answering

Published in Computational Linguistics, 2024

Transformer-based language models have been shown to be highly effective for several NLP tasks. In this article, we consider three transformer models, BERT, RoBERTa, and XLNet, in both small and large versions, and investigate how faithful their representations are with respect to the semantic content of texts. We formalize a notion of semantic faithfulness, in which the semantic content of a text should causally figure in a model’s inferences in question answering Read more

Recommended citation: Chaturvedi, A., Bhar, S., Saha, S., Garain, U., & Asher, N. (2024). Analyzing Semantic Faithfulness of Language Models via Input Intervention on Question Answering. Computational Linguistics, 50(1), 119-155.

Limits for Learning with Language Models

Published in Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023), 2023

Nevertheless, several recent papers provide empirical evidence that LLMs fail to capture important aspects of linguistic meaning. Focusing on universal quantification, we provide a theoretical foundation for these empirical findings by proving that LLMs cannot learn certain fundamental semantic properties including semantic entailment and consistency as they are defined in formal semantics. More generally, we show that LLMs are unable to learn concepts beyond the first level of the Borel Hierarchy, which imposes severe limits on the ability of LMs, both large and small, to capture many aspects of linguistic meaning. This means that LLMs will continue to operate without formal guarantees on tasks that require entailments and deep linguistic understanding. Read more

Recommended citation: Asher, N., Bhar, S., Chaturvedi, A., Hunter, J., & Paul, S. (2023). Limits for Learning with Language Models. In Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023) (pp. 236–248).