Publications

1. ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
   Nikhil Anand, Shwetha Somasundaram, Anirudh Phukan, Apoorv Saxena, and Koyel Mukherjee
   arXiv preprint arXiv:2601.04131, 2026 [Under Review at CoNLL 2026]
   arXiv

   PDF
2. Masking or Mitigating? Deconstructing the Impact of Query Rewriting on Retriever Biases in RAG
   Agam Goyal, Koyel Mukherjee, Apoorv Saxena, Anirudh Phukan, Eshwar Chandrasekharan, and Hari Sundaram
   In Findings of the Association for Computational Linguistics: ACL 2026
   ACL Findings

   PDF

1. Beyond Logit Lens: Contextual Embeddings for Robust Hallucination Detection & Grounding in VLMs
   Anirudh Phukan, Divyansh, Harshit Kumar Morj, Vaishnavi, Apoorv Saxena, and Koustava Goswami
   In Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies
   NAACL

   PDF
2. PLD+: Accelerating LLM inference by leveraging Language Model Artifacts
   Shwetha Somasundaram, Anirudh Phukan, and Apoorv Saxena
   In Findings of the Association for Computational Linguistics: NAACL 2025
   NAACL Findings

   PDF

1. Peering into the Mind of Language Models: An Approach for Attribution in Contextual Question Answering
   Anirudh Phukan, Shwetha Somasundaram, Apoorv Saxena, Koustava Goswami, and Balaji Vasan Srinivasan
   In Findings of the Association for Computational Linguistics: ACL 2024
   ACL Findings

   PDF
2. IPCL: Iterative Pseudo-Supervised Contrastive Learning to Improve Self-Supervised Feature Representation
   S. Kumar*, A. Phukan* and A. Sur
   2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
   ICASSP

   PDF