Himabindu Lakkaraju

University of Massachusetts Amherst — United States

Computer Science · Physical Sciences

29h-index5.9kcitations158works1.72yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Explainable Artificial Intelligence (XAI)(63), Adversarial Robustness in Machine Learning(36), Machine Learning and Data Classification(24), Topic Modeling(21), Artificial Intelligence in Healthcare and Education(15)

Publications158 total

Towards Uncovering How Large Language ModelsWork: An Interpretability Perspective
ACM SIGKDD Explorations Newsletter·2025
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability
arXiv (Cornell University)·2025Open Access
Detecting LLM-generated peer reviews
PLoS ONE·2025· 3 citedOpen Access
Inference-Time Reward Hacking in Large Language Models
arXiv (Cornell University)·2025Open Access
Soft Best-of-$n$ Sampling for Model Alignment
2025
Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems
arXiv (Cornell University)·2025Open Access
Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders
ArXiv.org·2025Open Access
Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
arXiv (Cornell University)·2025Open Access
Soft Best-of-n Sampling for Model Alignment
arXiv (Cornell University)·2025Open Access
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence
arXiv (Cornell University)·2025Open Access
Towards Interpretable Soft Prompts
arXiv (Cornell University)·2025Open Access
Detecting LLM-Generated Peer Reviews
arXiv (Cornell University)·2025Open Access
Counterfactual Explanations May Not Be the Best Algorithmic Recourse Approach
2025· 5 cited
On the Impact of Fine-Tuning on Chain-of-Thought Reasoning
2025· 3 citedOpen Access
A Survey of Data Attribution: Methods, Applications, and Evaluation in the Era of Generative AI
SSRN Electronic Journal·2025Open Access
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models
arXiv (Cornell University)·2024Open Access
On the Impact of Fine-Tuning on Chain-of-Thought Reasoning
arXiv (Cornell University)·2024Open Access
Towards Unifying Interpretability and Control: Evaluation via Intervention
arXiv (Cornell University)·2024Open Access
On the Trade-offs between Adversarial Robustness and Actionable Explanations
Proceedings of the AAAI/ACM Conference on AI Ethics and Society·2024Open Access
Generalized Group Data Attribution
arXiv (Cornell University)·2024Open Access
page 1 of 8Next →

Frequent Co-authors

Jure Leskovec(10), Dylan Slack(8), Sameer Singh(8), Chirag Agarwal(7), Sophie Hilgard(6), Ece Kamar(6), Rich Caruana(5), Marinka Žitnik(5), Jon Kleinberg(4), Sendhil Mullainathan(4), Jens Ludwig(3), Emily Jia(3), Satyapriya Krishna(3), Shahin Jabbari(3), Martin Pawelczyk(3), Sohini Upadhyay(3), Kaivalya Rawal(3), Stephen H. Bach(2), Osbert Bastani(2), Everaldo Aguiar(2)