Elamur Research⌕
☰
home / authors / Chirag Agarwal

Chirag Agarwal

Chirag Agarwal has 4 papers in our library, in 2023–2026, most of them on Language models & pretraining, Reasoning, Multilingual & cross-lingual NLP; often with Akash Ghosh, Aounon Kumar, Himabindu Lakkaraju.

4 papers in our library · 2023–2026

OpenAlex · ORCID · Wikidata · h-index 16 · 91 works · 938 citations OpenAlex, 2026-10-14

📄 4 works in our library · 🔗 Cited 94 times in our library · ⭐ Paper Stars ranking: #6559

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

Elsewhere: Google Scholar · Semantic Scholar · dblp · ACL Anthology

 Affiliations

🎓University of VirginiaCharlottesville · United States2024–2026 · 23 paperscurrent🎓Harvard UniversityCambridge · United States2020–2026 · 22 paperscurrent🎓University of Illinois ChicagoChicago · United States2017–2020 · 16 papers🏢Adobe SystemsSan Jose · United States2022–2023 · 4 papers🏥Geisinger Health SystemDanville · United States2017–2018 · 4 papers

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 7The field of science this work belongs to (OpenAlex fields).Computer Science · 4 worksArtificial Intelligence · 4 worksArts and Humanities · 2 worksLanguage and Linguistics · 2 worksMedicine · 1 workComputer Vision and Pattern Recognition · 2 worksHealth Informatics · 1 work

🧭 Topics 5Research subjects and languages the work is about.Language models & pretraining · 2 worksBias, fairness & safety · 1 workReasoning · 2 worksMultilingual & cross-lingual NLP · 1 workEvaluation & benchmarks · 1 work

 Works by year

2020s

20263 papers20231 paper

 Papers

The most cited first (OpenAlex and our library).

  1. Certifying LLM Safety against Adversarial Prompting (2023 · 113 citations)
    Safety-aligned LLMs can still be jailbroken when an attacker attaches crafted adversarial tokens to a harmful request.
  2. CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning (2026 · 5 citations)
    Large language models handle math and commonsense reasoning reasonably well in English, but they often fail at medical reasoning in other languages.
  3. A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models (2026 · 1 citation)
    Graph-Language Models (GLMs) pair a GNN encoder with an LLM. This paper asks whether the benchmarks used to evaluate them actually test joint reasoning over graph structure and text. The authors re-run standard evaluations on node classification and link prediction, in both supervised and zero-shot settings. They…
  4. Towards Understanding the Robustness of Sparse Autoencoders (2026)
    Jailbreak attacks that optimize adversarial suffixes against an LLM's internals remain a serious threat. It is also unclear how Sparse Autoencoders (SAEs), normally used for interpretability, affect this vulnerability. The authors splice pretrained SAEs into the residual stream of one intermediate layer at inference…

 Co-authors here

7 co-authors with a page, the most papers together first.

Venues

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

 Cited by

Papers of our library cite their works 94 times (of the 149,439 papers whose bibliographies we read); 18 citing papers with a page here →.

Updated

This page in Markdown → https://md.research.elamur.ai/free/en/authors/chirag-agarwal/