Milan Bhan

According to our database1, Milan Bhan authored at least 9 papers between 2023 and 2026.

Collaborative distances:
  • Dijkstra number2 of five.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
Towards Faithful Multimodal Concept Bottleneck Models.
CoRR, March, 2026

2025
In-Distribution Steering: Balancing Control and Coherence in Language Model Generation.
CoRR, October, 2025

Did I Faithfully Say What I Thought? Bridging the Gap Between Neural Activity and Self-Explanations in Large Language Models.
CoRR, June, 2025

Towards Achieving Concept Completeness for Unsupervised Textual Concept Bottleneck Models.
CoRR, February, 2025

Mitigating Text Toxicity with Counterfactual Generation.
Proceedings of the Explainable Artificial Intelligence, 2025

Towards Achieving Concept Completeness for Textual Concept Bottleneck Models.
Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

2024
Self-AMPLIFY: Improving Small Language Models with Self Post Hoc Explanations.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023
Evaluating Self-attention Interpretability Through Human-Grounded Experimental Protocol.
Proceedings of the Explainable Artificial Intelligence, 2023

TIGTEC: Token Importance Guided TExt Counterfactuals.
Proceedings of the Machine Learning and Knowledge Discovery in Databases: Research Track, 2023


  Loading...