Kishan Maharaj — accepted AI-conference papers

2025

ETF: An Entity Tracing Framework for Hallucination Detection in Code Summaries

Kishan Maharaj, Vitobha Munigala, Srikanth G. Tamilselvam, Prince Kumar, Sayandeep Sen, Palani Kodeswaran +2

ACL 2025long

Recent advancements in large language models (LLMs) have significantly enhanced their ability to understand both natural language and code, driving their use in tasks like natural language-to-code (NL2Code) and code summarisation. However, LLMs are prone to hallucination—outputs that stray from inte…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Understand the Implication: Learning to Think for Pragmatic Understanding

Settaluri Lakshmi Sravanthi, Kishan Maharaj, Sravani Gunnu, Abhijit Mishra, Pushpak Bhattacharyya

ACL 2025finding

Pragmatics, the ability to infer meaning beyond literal interpretation, is crucial for social cognition and communication. While LLMs have been benchmarked for their pragmatic understanding, improving their performance remains underexplored. Existing methods rely on annotated labels but overlook the…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

Mental Disorder Classification via Temporal Representation of Text

Raja Kumar, Kishan Maharaj, Ashita Saxena, Pushpak Bhattacharyya

EMNLP 2024finding

Mental disorders pose a global challenge, aggravated by the shortage of qualified mental health professionals. Mental disorder prediction from social media posts by current LLMs is challenging due to the complexities of sequential text data and the limited context length of language models. Current…

Cited by 5 Source ↗PDF ↗Scholar ↗

2023

Eyes Show the Way: Modelling Gaze Behaviour for Hallucination Detection

Kishan Maharaj, Ashita Saxena, Raja Kumar, Abhijit Mishra, Pushpak Bhattacharyya

EMNLP 2023long findings

Detecting hallucinations in natural language processing (NLP) is a critical undertaking that demands a deep understanding of both the semantic and pragmatic aspects of languages. Cognitive approaches that leverage users’ behavioural signals, such as gaze, have demonstrated effectiveness in addressin…

Cited by 7 Source ↗Scholar ↗