HL
Himabindu Lakkaraju
cs.LGcs.AIcs.CLstat.MLcs.CRcs.CYcs.CVcs.HCcs.MAcs.SI
On Valency
published · living versionsW_gh3ttxwt·v1 · currentpublished
Alignment Myopia in Generative AI
with Remi Denton, Aida Davani, Cynthia L Bennett, Michael Madaio +1
1 version
Preprints & journals
106 papers in the corpus · 2012–2026Learning Self-Orchestration in Decentralized Agent Swarms2610.22322v2 · Guowei Xu, Zhenting Qi, Amani Kiruga et al.2026 · 0 citationsarXiv
Scaling Multi-Agent Intelligence with Substrate-Centric Coordination2610.16120v1 · Zhenting Qi, Zhuokai Zhao, Rulin Shao et al.2026 · 0 citationsarXiv
Prototype Language Models2607.00510v1 · Dan Ley, Giang Nguyen, Himabindu Lakkaraju et al.2026 · 0 citationsarXiv
A reporting checklist for large language models in behavioural science.42265331 · Feuerriegel, Stefan, Barrie, Christopher, Crockett, M J et al.2026 · 16 citationsNature human behaviour. 2026;10(7):1182-1186
Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods2607.14123v1 · Michal Moshkovitz, Suraj Srinivas, Lesia Semenova et al.2026 · 0 citationsProceedings of the 43rd International Conference on Machine Learning, Seoul, South Korea. PMLR 306, 2026
Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions2606.02859v2 · Zhenting Qi, Huangyuan Su, Ao Qu et al.2026 · 0 citationsarXiv
Self-Improving Language Models with Bidirectional Evolutionary Search2605.28814v2 · Guowei Xu, Zhenting Qi, Huangyuan Su et al.2026 · 0 citationsarXiv
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting2605.18810v1 · Tianyu Wu, Yu Yao, Zhenting Qi et al.2026 · 0 citationsarXiv
Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning2602.03978v1 · Zidi Xiong, Shan Chen, Himabindu Lakkaraju2026 · 0 citationsarXiv
Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability2511.05541v2 · Usha Bhalla, Alex Oesterling, Claudio Mayrink Verdun et al.2025 · 0 citationsarXiv
Detecting LLM-generated peer reviews.40982562 · Rao, Vishisht Srihari, Kumar, Aounon, Lakkaraju, Himabindu et al.2025 · 16 citationsPloS one. 2025;20(9):e0331871
Advancing science- and evidence-based AI policy.40743343 · Bommasani, Rishi, Arora, Sanjeev, Chayes, Jennifer et al.2025 · 22 citationsScience (New York, N.Y.). 2025;389(6759):459-461
Inference-Time Reward Hacking in Large Language Models2506.19248v2 · Hadi Khalaf, Claudio Mayrink Verdun, Alex Oesterling et al.2025 · 2 citationsarXiv
EvoLM: In Search of Lost Language Model Training Dynamics2506.16029v2 · Zhenting Qi, Fan Nie, Alexandre Alahi et al.2025 · 0 citationsarXiv
Who Gets Credit or Blame? Attributing Accountability in Modern AI Systems2506.00175v5 · Shichang Zhang, Hongzhe Du, Jiaqi W. Ma et al.2025 · 0 citationsarXiv
Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders2505.16004v2 · Aaron J. Li, Suraj Srinivas, Usha Bhalla et al.2025 · 0 citationsarXiv
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior2505.16067v2 · Zidi Xiong, Yuping Lin, Wenya Xie et al.2025 · 6 citationsarXiv
Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models2505.13774v2 · Zidi Xiong, Shan Chen, Zhenting Qi et al.2025 · 1 citationarXiv
Soft Best-of-n Sampling for Model Alignment2505.03156v1 · Claudio Mayrink Verdun, Alex Oesterling, Himabindu Lakkaraju et al.2025 · 2 citationsarXiv
How Post-Training Reshapes LLMs: A Mechanistic View on Knowledge, Truthfulness, Refusal, and Confidence2504.02904v3 · Hongzhe Du, Weikai Li, Min Cai et al.2025 · 0 citationsarXiv
Towards Interpretable Soft Prompts2504.02144v1 · Oam Patel, Jason Wang, Nikhil Shivakumar Nayak et al.2025 · 0 citationsarXiv
Towards Unified Attribution in Explainable AI, Data-Centric AI, and Mechanistic Interpretability2501.18887v3 · Shichang Zhang, Tessa Han, Usha Bhalla et al.2025 · 0 citationsarXiv
Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models2501.00418v1 · Martin Pawelczyk, Lillian Sun, Zhenting Qi et al.2024 · 0 citationsarXiv
On the Impact of Fine-Tuning on Chain-of-Thought Reasoning2411.15382v2 · Elita Lobo, Chirag Agarwal, Himabindu Lakkaraju2024 · 4 citationsarXiv
Towards Unifying Interpretability and Control: Evaluation via Intervention2411.04430v2 · Usha Bhalla, Suraj Srinivas, Asma Ghandeharioun et al.2024 · 0 citationsarXiv
Generalized Group Data Attribution2410.09940v2 · Dan Ley, Suraj Srinivas, Shichang Zhang et al.2024 · 0 citationsarXiv
Quantifying Generalization Complexity for Large Language Models2410.01769v2 · Zhenting Qi, Hongyin Luo, Xuliang Huang et al.2024 · 0 citationsarXiv
Learning Recourse Costs from Pairwise Feature Comparisons2409.13940v1 · Kaivalya Rawal, Himabindu Lakkaraju2024 · 0 citationsarXiv
Explaining the Model, Protecting Your Data: Revealing and Mitigating the Data Privacy Risks of Post-Hoc Model Explanations via Membership Inference2407.17663v1 · Catherine Huang, Martin Pawelczyk, Himabindu Lakkaraju2024 · 0 citationsarXiv
All Roads Lead to Rome? Exploring Representational Similarities Between Latent Spaces of Generative Image Models2407.13449v1 · Charumathi Badrinath, Usha Bhalla, Alex Oesterling et al.2024 · 0 citationsarXiv
Operationalizing the Blueprint for an AI Bill of Rights: Recommendations for Practitioners, Researchers, and Policy Makers2407.08689v1 · Alex Oesterling, Usha Bhalla, Suresh Venkatasubramanian et al.2024 · 5 citationsarXiv
On the Hardness of Faithful Chain-of-Thought Reasoning in Large Language Models2406.10625v2 · Sree Harsha Tanneru, Dan Ley, Chirag Agarwal et al.2024 · 1 citationarXiv
Interpretability Needs a New Paradigm2405.05386v2 · Andreas Madsen, Himabindu Lakkaraju, Siva Reddy et al.2024 · 4 citationsarXiv
More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness2404.18870v2 · Aaron J. Li, Satyapriya Krishna, Himabindu Lakkaraju2024 · 0 citationsarXiv
Manipulating Large Language Models to Increase Product Visibility2404.07981v2 · Aounon Kumar, Himabindu Lakkaraju2024 · 2 citationsarXiv
Data Poisoning Attacks on Off-Policy Policy Evaluation Methods2404.04714v1 · Elita Lobo, Harvineet Singh, Marek Petrik et al.2024 · 0 citationsarXiv
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models2403.03744v5 · Tessa Han, Aounon Kumar, Chirag Agarwal et al.2024 · 11 citationsarXiv
Follow My Instruction and Spill the Beans: Scalable Data Extraction from Retrieval-Augmented Generation Systems2402.17840v3 · Zhenting Qi, Hanlin Zhang, Eric Xing et al.2024 · 6 citationsarXiv
OpenHEXAI: An Open-Source Framework for Human-Centered Evaluation of Explainable Machine Learning2403.05565v1 · Jiaqi Ma, Vivian Lai, Yiming Zhang et al.2024 · 0 citationsarXiv
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)2402.10376v2 · Usha Bhalla, Alex Oesterling, Suraj Srinivas et al.2024 · 19 citationsarXiv
Towards Uncovering How Large Language Model Works: An Explainability Perspective2402.10688v2 · Haiyan Zhao, Fan Yang, Bo Shen et al.2024 · 7 citationsarXiv
Understanding the Effects of Iterative Prompting on Truthfulness2402.06625v1 · Satyapriya Krishna, Chirag Agarwal, Himabindu Lakkaraju2024 · 4 citationsarXiv
Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models2402.04614v3 · Chirag Agarwal, Sree Harsha Tanneru, Himabindu Lakkaraju2024 · 14 citationsarXiv
Computational Copyright: Towards A Royalty Model for Music Generative AI2312.06646v5 · Junwei Deng, Xirui Jiang, Shiyuan Zhang et al.2023 · 2 citationsarXiv
Is Ignorance Bliss? The Role of Post Hoc Explanation Faithfulness and Alignment in Model Trust in Laypeople and Domain Experts2312.05690v2 · Tessa Han, Yasha Ektefaie, Maha Farhat et al.2023 · 0 citationsarXiv
A Study on the Calibration of In-context Learning2312.04021v4 · Hanlin Zhang, Yi-Fan Zhang, Yaodong Yu et al.2023 · 3 citationsarXiv
Quantifying Uncertainty in Natural Language Explanations of Large Language Models2311.03533v1 · Sree Harsha Tanneru, Chirag Agarwal, Himabindu Lakkaraju2023 · 3 citationsarXiv
Confronting LLMs with Traditional ML: Rethinking the Fairness of Large Language Models in Tabular Classifications2310.14607v2 · Yanchen Liu, Srishti Gautam, Jiaqi Ma et al.2023 · 16 citationsarXiv
In-Context Unlearning: Language Models as Few Shot Unlearners2310.07579v4 · Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju2023 · 20 citationsarXiv
In-Context Explainers: Harnessing LLMs for Explaining Black Box Models2310.05797v4 · Nicholas Kroeger, Dan Ley, Satyapriya Krishna et al.2023 · 6 citationsarXiv
Career total: 167 works. 106 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.