🧑‍🔬 Ameeta Agrawal

🏛️ Affiliations

🎓Portland State UniversityPortland · United States2021–2026 · 54 papersEmploymentcurrent🎓York UniversityToronto · Canada2012–2020 · 10 papers

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.

📅 Works by year

2020s

📄 Papers

The most cited first (OpenAlex and our library).

1. What Drives Performance in Multilingual Language Models? (2024 · 20 citations)
   The authors ask why multilingual large language models (MLLMs) succeed in some languages and fail in others, with special attention to languages a model never saw during pretraining.
2. Evaluating Multilingual Long-Context Models for Retrieval and Reasoning (2024 · 13 citations)
   Long-context LLMs score almost perfectly on synthetic "needle in a haystack" tests, but these tests mostly use English and hide only one target fact.
3. Self-Explaining Hate Speech Detection with Moral Rationales (2026 · 2 citations)
   Hate speech classifiers often depend on surface lexical cues. This makes them prone to spurious correlations, hard to interpret and weak with culturally contingent language. The authors argue that moral values, framed through Moral Foundations Theory, give a more stable signal than wording alone. They propose…
4. No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned Generation (2026 · 1 citation)
   LLMs given external passages, such as retrieved evidence in RAG, sometimes change an answer they already had right, even when the passage adds nothing useful.
5. ThreadSumm: Summarization of Nested Discourse Threads Using Tree of Thoughts (2026)
   Forum discussions form tree-like threads where replies, quotes and side topics interleave. Standard LLM summarizers often flatten this structure and drop minority viewpoints or lose logical flow. The authors propose ThreadSumm, a staged LLM pipeline that treats thread summarization as structured reasoning.

All works

6 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. What Drives Performance in Multilingual Language Models?Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial)Sina Bagheri Nezhad, Ameeta Agrawal2024 · 20 citations
2. Evaluating Multilingual Long-Context Models for Retrieval and ReasoningWorkshop on Multilingual Representation LearningAmeeta Agrawal, Andy Dang, Sina Bagheri Nezhad, et al.2024 · 13 citations
3. Emotion and Sentiment Guided Paraphrasing ↗Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis · no summary yetJustin Xie, Ameeta Agrawal2023 · 6 citations
4. Self-Explaining Hate Speech Detection with Moral RationalesFindings of the Association for Computational LinguisticsFrancielle Vargas, Jackson Trager, Diego Alves, et al.2026 · 2 citations
5. No-Worse Context-Aware Decoding: Preventing Neutral Regression in Context-Conditioned GenerationFindings of the Association for Computational LinguisticsYufei Tao, Ameeta Agrawal2026 · 1 citation
6. ThreadSumm: Summarization of Nested Discourse Threads Using Tree of ThoughtsAnnual Meeting of the Association for Computational Linguistics (ACL)Olubusayo Olabisi, Ekata Mitra, Ameeta Agrawal2026

🤝 Co-authors here

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

• Sina Bagheri Nezhad ×2
• Daryna Dementieva
• Diego Alves
• Jackson Trager
• Matteo Guida
• Surendrabikram Thapa

Venues

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

• Findings of the Association for Computational Linguistics ×2: Findings of the Association for Computational Linguistics 2026 ×2
• Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
• Workshop on Multilingual Representation Learning: Workshop on Multilingual Representation Learning 2024
• Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial): VarDial 2024
• Proceedings of the 13th Workshop on Computational Approaches to Subjectivity, Sentiment, & Social Media Analysis

🔗 Cited by

Papers of our library cite their works 29 times (of the 149,439 papers whose bibliographies we read); 5 citing papers with a page here →.

Updated 1 November 2026

↑ back to top

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