Elamur Research⌕
☰
home / authors / Anil Ramakrishna

Anil Ramakrishna

Anil Ramakrishna has 3 papers in our library, in 2026, most of them on Language models & pretraining, Semantic parsing & meaning representation, Bias, fairness & safety; often with Kai-Wei Chang, Rahul Gupta, Aram Galstyan.

3 papers in our library · 2026

OpenAlex · ORCID · h-index 8 · 50 works · 309 citations OpenAlex, 2026-10-14

📄 3 works in our library · 🔗 Cited 28 times in our library · 7 more in our library without a page yet · ⭐ Paper Stars ranking: #10641

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

🏢AmazonSeattle · United States2021–2025 · 14 paperscurrent🎓Arizona State UniversityTempe · United States2025 · 1 papercurrent🎓University of Illinois Urbana-ChampaignUrbana · United States2025 · 1 papercurrent🎓University of Southern CaliforniaLos Angeles · United States2013–2024 · 15 papersEducation · Doctor of Philosophy, Computer Science

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine.

 Fields, topics and concepts

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

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Artificial Intelligence · 3 worksArts and Humanities · 3 worksComputer Science · 3 worksLanguage and Linguistics · 3 worksComputer Vision and Pattern Recognition · 1 work

🧭 Topics 3Research subjects and languages the work is about.Language models & pretraining · 2 worksBias, fairness & safety · 1 workSemantic parsing & meaning representation · 1 work

 Works by year

2020s

20263 papers

 Papers

The most cited first (OpenAlex and our library).

  1. BLUR: A Bi-Level Optimization Approach for LLM Unlearning (2026 · 4 citations)
    Most LLM unlearning methods minimize a weighted sum of a forget loss and a retain loss with a fixed coefficient.
  2. From Narrow Unlearning to Emergent Misalignment in LLMs (2026)
    Earlier work found that fine-tuning an aligned LLM on a narrow task, such as writing insecure code, can cause emergent misalignment (EMA): harmful behaviour that spreads to unrelated domains.
  3. SWAN: Semantic Watermarking with Abstract Meaning Representation (2026)
    Watermarks for LLM-generated text are usually planted at the token level by biasing which tokens the decoder picks.

All works

10 works of theirs in our library, the most cited first; 3 with a page here, the others link their original until we summarise them.

  1. Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM ↗Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing · no summary yetHaw-Shiuan Chang et al.2024 · 8 citations
  2. REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy ↗arXiv (Cornell University) · no summary yetHaw-Shiuan Chang et al.2024 · 8 citations
  3. BLUR: A Bi-Level Optimization Approach for LLM UnlearningConference of the European Chapter of the Association for Computational Linguistics (EACL)Hadi Reisizadeh, Jinghan Jia, Zhiqi Bu, et al.2026 · 4 citations
  4. JAB: Joint Adversarial Prompting and Belief Augmentation ↗arXiv (Cornell University) · no summary yetNinareh Mehrabi et al.2023 · 4 citations
  5. REAL Sampling: Boosting Factuality and Diversity of Open-ended Generation by Extrapolating the Entropy of an Infinitely Large LM ↗Transactions of the Association for Computational Linguistics · no summary yetHaw-Shiuan Chang et al.2025 · 3 citations
  6. Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification ↗Findings of the Association for Computational Linguistics: EMNLP 2024 · no summary yetTao Meng et al.2024 · 3 citations
  7. Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation ↗Findings of the Association for Computational Linguistics: ACL 2025 · no summary yetTharindu Kumarage et al.2025 · 2 citations
  8. From Narrow Unlearning to Emergent Misalignment in LLMsAnnual Meeting of the Association for Computational Linguistics (ACL)Erum Mushtaq, Anil Ramakrishna, Satyapriya Krishna, et al.2026
  9. SWAN: Semantic Watermarking with Abstract Meaning RepresentationAnnual Meeting of the Association for Computational Linguistics (ACL)Ziping Ye, Gourab Dey, Christos Christodoulopoulos, et al.2026
  10. Partial Federated Learning ↗arXiv (Cornell University) · no summary yetTiantian Feng et al.2024

 Co-authors here

11 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 28 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated

↑ back to top

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