← Authors

Himabindu Lakkaraju

41 papers · 2016–2026 · 8 conferences · across top CS/AI conferences

Achievements

πŸƒ Academic Marathon (9) πŸŒ‰ Interdisciplinary Bridge 🐝 Cross-Pollinator (13) 🌈 Renaissance Researcher (8) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (51) 🧭 Keyword Pioneer 🌍 Conference Polyglot (7) πŸ”¬ Deep Specialist (20) πŸ† Keyword Champion (2) πŸ‘‘ Triple Crown πŸ† Grand Slam 🧬 Topic Evolution πŸ”₯ Unstoppable (6) ⚑ Prolific Year (7) πŸ’Ž Century Club (40) ❓ The Questioner (3) πŸ—ƒοΈ Keyword Collector (147)

Conferences

NIPS (16) AISTATS (6) ICML (6) ICLR (4) UAI (4) NAACL (3) AAAI (1) EACL (1)

Top co-authors

Chirag Agarwal (9) Suraj Srinivas (8) Satyapriya Krishna (5) Martin Pawelczyk (5) Jiaqi Ma (4) Tessa Han (3) Sohini Upadhyay (3) Marinka Zitnik (3) Usha Bhalla (3) Dylan Slack (3)

Research topics

Privacy (1)

Keywords

counterfactual explanation (5) large language model (5) feature attribution (4) post hoc explanation (4) model interpretability (4) adversarial training (4) uncertainty quantification (3) algorithmic recourse (3) algorithmic fairness (3) adversarial robustness (3) benchmark evaluation (2) chain-of-thought prompting (2) right to be forgotten (2) post-hoc explanation (2) data deletion (2) generative model (2) interpretable model (2) causal inference (2) in-context learning (2) explainable ai (2)

Papers

Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders EACL 2026
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems ICLR 2025
On the Impact of Fine-Tuning on Chain-of-Thought Reasoning NAACL 2025
More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness ICLR 2025
Quantifying Generalization Complexity for Large Language Models ICLR 2025
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE) NIPS 2024
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models NIPS 2024
Quantifying Uncertainty in Natural Language Explanations of Large Language Models AISTATS 2024
Fair Machine Unlearning: Data Removal while Mitigating Disparities AISTATS 2024
Understanding the Effects of Iterative Prompting on Truthfulness ICML 2024
In-Context Unlearning: Language Models as Few-Shot Unlearners ICML 2024
Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications NAACL 2024
A Study on the Calibration of In-context Learning NAACL 2024
Characterizing Data Point Vulnerability as Average-Case Robustness UAI 2024
On Minimizing the Impact of Dataset Shifts on Actionable Explanations UAI 2023
On the Privacy Risks of Algorithmic Recourse AISTATS 2023
Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse ICLR 2023
On the Impact of Algorithmic Recourse on Social Segregation ICML 2023
Towards Bridging the Gaps between the Right to Explanation and the Right to be Forgotten ICML 2023
$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models NIPS 2023
Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness NIPS 2023
Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability NIPS 2023
Post Hoc Explanations of Language Models Can Improve Language Models NIPS 2023
Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations NIPS 2022
OpenXAI: Towards a Transparent Evaluation of Model Explanations NIPS 2022
Efficient Training of Low-Curvature Neural Networks NIPS 2022
Data poisoning attacks on off-policy policy evaluation methods UAI 2022
Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysis AISTATS 2022
Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methods AISTATS 2022
Towards Robust and Reliable Algorithmic Recourse NIPS 2021
Reliable Post hoc Explanations: Modeling Uncertainty in Explainability NIPS 2021
Towards a unified framework for fair and stable graph representation learning UAI 2021
Learning Models for Actionable Recourse NIPS 2021
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations ICML 2021
Fair Influence Maximization: a Welfare Optimization Approach AAAI 2021
Counterfactual Explanations Can Be Manipulated NIPS 2021
Beyond Individualized Recourse: Interpretable and Interactive Summaries of Actionable Recourses NIPS 2020
Incorporating Interpretable Output Constraints in Bayesian Neural Networks NIPS 2020
Robust and Stable Black Box Explanations ICML 2020
Learning Cost-Effective and Interpretable Treatment Regimes AISTATS 2017
Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making NIPS 2016