---
title: "Himabindu Lakkaraju · Google — author profile and papers"
description: "Himabindu Lakkaraju, Google: 5 papers on Elamur Research (2023–2026), h-index 29 — affiliations, topics, co-authors and who cites them in…"
canonical: "https://research.elamur.ai/free/en/authors/himabindu-lakkaraju/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/himabindu-lakkaraju/)

[home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Himabindu Lakkaraju

# Himabindu Lakkaraju

Himabindu Lakkaraju has 5 papers in our library, in 2023–2026, most of them on [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Reasoning](https://md.research.elamur.ai/free/en/topics/reasoning/), [Interpretability](https://md.research.elamur.ai/free/en/topics/interpretability/); often with [Aounon Kumar](https://md.research.elamur.ai/free/en/authors/aounon-kumar/), [Martin Pawelczyk](https://md.research.elamur.ai/free/en/authors/martin-pawelczyk/), [Chirag Agarwal](https://md.research.elamur.ai/free/en/authors/chirag-agarwal/).

5 papers in our library · 2023–2026

[OpenAlex](https://openalex.org/A5015520086) · [ORCID](https://orcid.org/0000-0001-7922-6544) · [Wikidata](https://www.wikidata.org/wiki/Q70882189) · [**h-index 29**](https://openalex.org/authors/A5015520086) · [171 works](https://openalex.org/works?filter=author.id:A5015520086) · [6,348 citations](https://openalex.org/works?filter=author.id:A5015520086&sort=cited_by_count:desc) OpenAlex, 2026-10-14

[📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/himabindu-lakkaraju/#papers) · [🔗 Cited 245 times in our library](https://md.research.elamur.ai/free/en/authors/himabindu-lakkaraju/cited-by/) · [17 more in our library without a page yet](#also) · [⭐ Paper Stars ranking: #6089](https://md.research.elamur.ai/free/en/paper-stars/page/61/#star-6089)

The profile is the library's match of the name; two people with one name are not always told apart.

Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Himabindu+Lakkaraju) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Himabindu+Lakkaraju) · [dblp](https://dblp.org/search?q=Himabindu+Lakkaraju) · [ACL Anthology](https://aclanthology.org/search/?q=Himabindu+Lakkaraju)

## Affiliations

[🎓**Harvard University** Cambridge · United States 2019–2026 · 98 papers*current*](https://md.research.elamur.ai/free/en/universities/harvard-university/) · [🏢**Google** Mountain View · United States 2026 · 1 paper*current*](https://md.research.elamur.ai/free/en/companies/google/) · [🎓**Harvard–MIT Division of Health Sciences and Technology** Cambridge · United States 2026 · 1 paper*current*](https://ror.org/00jjeh629) · [🎓**Stanford University** Stanford · United States 2012–2021 · 20 papers](https://md.research.elamur.ai/free/en/universities/stanford-university/) · [🔬**IBM Research - India** New Delhi · India 2011–2012 · 5 papers](https://md.research.elamur.ai/free/en/labs/ibm-research-india/) · [🎓**University of Illinois Urbana-Champaign** Urbana · United States 2023–2024 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-illinois-urbana-champaign/) · [🏢**IBM** Bengaluru · India 2011–2012 · 3 papers](https://md.research.elamur.ai/free/en/companies/ibm-india/) · [🎓**UiT The Arctic University of Norway** Tromsø · Norway 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/uit-the-arctic-university-of-norway/)

🏛️**Harvard Business School** Massachusetts · [United States](https://md.research.elamur.ai/free/en/countries/united-states/) Employment

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 4 more institutions on single bylines are not listed.

## Fields, topics and concepts

Of its works in our library, with the number of works on each.

📚 Shelves 6 The field of science this work belongs to (OpenAlex fields).[Artificial Intelligence · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · [Computer Science · 5 works](https://md.research.elamur.ai/free/en/shelves/computer-science/) · [Arts and Humanities · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · [Language and Linguistics · 3 works](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · [Safety Research · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/safety-research/) · [Social Sciences · 1 work](https://md.research.elamur.ai/free/en/shelves/social-sciences/)

🧭 Topics 4 Research subjects and languages the work is about.[Language models & pretraining · 4 works](https://md.research.elamur.ai/free/en/topics/language-models/) · [Bias, fairness & safety · 1 work](https://md.research.elamur.ai/free/en/topics/bias-fairness-safety/) · [Interpretability · 1 work](https://md.research.elamur.ai/free/en/topics/interpretability/) · [Reasoning · 1 work](https://md.research.elamur.ai/free/en/topics/reasoning/)

## Works by year

### 2020s

[**2026** 2 papers](https://md.research.elamur.ai/free/en/authors/himabindu-lakkaraju/year/2026/) · [**2023** 3 papers](https://md.research.elamur.ai/free/en/authors/himabindu-lakkaraju/year/2023/)

## Papers

The most cited first (OpenAlex and our library).

1. **[Certifying LLM Safety against Adversarial Prompting](https://md.research.elamur.ai/free/en/papers/kumar-2023-certifying-llm-safety-against-adversarial/)** *(2023 · 113 citations)* Safety-aligned LLMs can still be jailbroken when an attacker attaches crafted adversarial tokens to a harmful request.
2. **[In-Context Unlearning: Language Models as Few Shot Unlearners](https://md.research.elamur.ai/free/en/papers/pawelczyk-2023-context-unlearning-language-models-few/)** *(2023 · 81 citations)* Privacy rules such as the Right to be Forgotten, along with copyright takedown demands, can require removing the effect of particular training examples from a deployed model.
3. **[Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions](https://md.research.elamur.ai/free/en/papers/wu-2023-analyzing-chain-thought-prompting-large/)** *(2023 · 30 citations)* Chain-of-thought (CoT) prompting is known to improve LLM accuracy on reasoning questions, but it is still unclear why it works.
4. **[How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://md.research.elamur.ai/free/en/papers/xiong-2026-how-memory-management-impacts-llm/)** *(2026 · 13 citations)* LLM agents often keep an episodic memory of earlier task queries and their execution trajectories, then retrieve similar records as in-context demonstrations.
5. **[Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models](https://md.research.elamur.ai/free/en/papers/sun-2026-generalizing-trust-weak-strong-trustworthiness/)** *(2026)* In high-stakes areas such as medicine, ground-truth labels are often missing, noisy or biased, so models must learn from imperfect supervision.

## All works

22 works of theirs in our library, the most cited first; 5 with a page here, the others link their original until we summarise them.

1. **[Human Decisions and Machine Predictions ↗](https://doi.org/10.1093/qje/qjx032) The Quarterly Journal of Economics · no summary yet**Jon M. Kleinberg et al.*2017 · 821 citations*
2. **[Interpretable Decision Sets ↗](https://doi.org/10.1145/2939672.2939874) ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · no summary yet**Himabindu Lakkaraju, Stephen H. Bach, Jure Leskovec*2016 · 670 citations*
3. **[Mining big data to extract patterns and predict real-life outcomes. ↗](https://doi.org/10.1037/met0000105) Psychological Methods · no summary yet**Michał Kosiński et al.*2016 · 201 citations*
4. **[The Selective Labels Problem ↗](https://doi.org/10.1145/3097983.3098066) ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) · no summary yet**Himabindu Lakkaraju et al.*2017 · 115 citations*
5. [**Certifying LLM Safety against Adversarial Prompting arXiv:2309.02705**Aounon Kumar, Chirag Agarwal, Suraj Srinivas, et al.*2023 · 113 citations*](https://md.research.elamur.ai/free/en/papers/kumar-2023-certifying-llm-safety-against-adversarial/)
6. **[Aspect Specific Sentiment Analysis Using Hierarchical Deep Learning ↗](https://openalex.org/W3049711450) no summary yet**Himabindu Lakkaraju, Richard Socher, Christopher D. Manning*2014 · 87 citations*
7. [**In-Context Unlearning: Language Models as Few Shot Unlearners arXiv:2310.07579**Martin Pawelczyk, Seth Neel, Himabindu Lakkaraju*2023 · 81 citations*](https://md.research.elamur.ai/free/en/papers/pawelczyk-2023-context-unlearning-language-models-few/)
8. **[Learning Cost-Effective and Interpretable Treatment Regimes ↗](https://openalex.org/W2645304696) International Conference on Artificial Intelligence and Statistics · no summary yet**Himabindu Lakkaraju, Cynthia D Rudin*2017 · 53 citations*
9. [**Analyzing Chain-of-Thought Prompting in Large Language Models via Gradient-based Feature Attributions arXiv:2307.13339**Skyler Wu, Eric Meng Shen, Charumathi Badrinath, et al.*2023 · 30 citations*](https://md.research.elamur.ai/free/en/papers/wu-2023-analyzing-chain-thought-prompting-large/)
10. **[Interpretable and Explorable Approximations of Black Box Models ↗](https://arxiv.org/abs/1707.01154) arXiv (Cornell University) · no summary yet**Himabindu Lakkaraju et al.*2017 · 29 citations*
11. **[Advancing science- and evidence-based AI policy ↗](https://doi.org/10.1126/science.adu8449) Science · no summary yet**Rishi Bommasani et al.*2025 · 25 citations*
12. **[A Bayesian Framework for Modeling Human Evaluations ↗](https://doi.org/10.1137/1.9781611974010.21) SIAM International Conference on Data Mining · no summary yet**Himabindu Lakkaraju et al.*2015 · 23 citations*
13. **[How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior](https://md.research.elamur.ai/free/en/papers/xiong-2026-how-memory-management-impacts-llm/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Zidi Xiong, Yuping Lin, Wenya Xie, et al.*2026 · 13 citations*
14. **[Learning Cost-Effective Treatment Regimes using Markov Decision Processes ↗](https://arxiv.org/abs/1610.06972) arXiv (Cornell University) · no summary yet**Himabindu Lakkaraju, Cynthia D Rudin*2016 · 12 citations*
15. **[Confusions over Time: An Interpretable Bayesian Model to Characterize Trends in Decision Making ↗](https://openalex.org/W2553480288) neural information processing systems · no summary yet**Himabindu Lakkaraju, Jure Leskovec*2016 · 8 citations*
16. **[Learning Cost-Effective and Interpretable Treatment Regimes for Judicial Bail Decisions ↗](https://openalex.org/W3049767819) no summary yet**Himabindu Lakkaraju, Cynthia D Rudin*2016 · 2 citations*
17. **[Psycho-Demographic Analysis of the Facebook Rainbow Campaign ↗](https://arxiv.org/abs/1610.05358) arXiv (Cornell University) · no summary yet**Wang, Yilun et al.*2016 · 2 citations*
18. **[Learning Cost-Effective and Interpretable Regimes for Treatment Recommendation ↗](https://arxiv.org/abs/1611.07663) arXiv (Cornell University) · no summary yet**Himabindu Lakkaraju, Cynthia D Rudin*2016 · 1 citation*
19. **[Generalizing Trust: Weak-to-Strong Trustworthiness in Language Models](https://md.research.elamur.ai/free/en/papers/sun-2026-generalizing-trust-weak-strong-trustworthiness/) [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/)**Lillian Sun, Martin Pawelczyk, Zhenting Qi, et al.*2026*
20. **[Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods ↗](https://arxiv.org/abs/2607.14123) arXiv (Cornell University) · no summary yet**Michal Moshkovitz et al.*2026*
21. **[Data Poisoning Attacks on Off-Policy Policy Evaluation Methods ↗](https://arxiv.org/abs/2404.04714) arXiv (Cornell University) · no summary yet**Elita Lobo et al.*2024*
22. **[Using Big Data to Improve Social Policy ↗](https://openalex.org/W3016395765) no summary yet**Himabindu Lakkaraju et al.*2014*

## Co-authors here

12 of 13 co-authors with a page, the most papers together first.

- [Aounon Kumar](https://md.research.elamur.ai/free/en/authors/aounon-kumar/) ×2
- [Martin Pawelczyk](https://md.research.elamur.ai/free/en/authors/martin-pawelczyk/) ×2
- [Chirag Agarwal](https://md.research.elamur.ai/free/en/authors/chirag-agarwal/)
- [Jiliang Tang](https://md.research.elamur.ai/free/en/authors/jiliang-tang/)
- [Pengfei He](https://md.research.elamur.ai/free/en/authors/pengfei-he/)
- [Seth Neel](https://md.research.elamur.ai/free/en/authors/seth-neel/)
- [Soheil Feizi](https://md.research.elamur.ai/free/en/authors/soheil-feizi/)
- [Wenya Xie](https://md.research.elamur.ai/free/en/authors/wenya-xie/)
- [Yuping Lin](https://md.research.elamur.ai/free/en/authors/yuping-lin/)
- [Zhen Xiang](https://md.research.elamur.ai/free/en/authors/zhen-xiang/)
- [Zhenting Qi](https://md.research.elamur.ai/free/en/authors/zhenting-qi/)
- [Zidi Xiong](https://md.research.elamur.ai/free/en/authors/zidi-xiong/)

## Venues

Where their works here were published, the most works first, with the editions of those that have a page.

- [Annual Meeting of the Association for Computational Linguistics (ACL)](https://md.research.elamur.ai/free/en/venues/acl/) ×2: [ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/) ×2
- ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD) ×2
- International Conference on Artificial Intelligence and Statistics
- Psychological Methods
- SIAM International Conference on Data Mining
- Science
- The Quarterly Journal of Economics
- neural information processing systems

## Cited by

Papers of our library cite their works 245 times (of the 149,439 papers whose bibliographies we read); [63 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/himabindu-lakkaraju/cited-by/).

Updated 2 November 2026