Robin Jia

About

I am an assistant professor in the Thomas Lord Department of Computer Science at the University of Southern California, where I lead the AI, Language, Learning, Generalization, and Robustness (Allegro) Lab. My research seeks to understand modern deep learning systems for NLP and ensure that they are reliable.

Research topics

• Natural Language Processing
• Computer Science
• Artificial Intelligence
• Information Retrieval
• Machine Learning
• Mathematics
• Econometrics
• Statistics
• Linguistics

Selected publications

• Mechanistic Interpretability of Emotion Inference in Large Language Models

  2025-01-01 · 3 citations

  articleOpen access

  Large language models (LLMs) show promising capabilities in predicting human emotions from text.However, the mechanisms through which these models process emotional stimuli remain largely unexplored.Our study addresses this gap by investigating how autoregressive LLMs infer emotions, showing that emotion representations are functionally localized to specific regions in the model.Our evaluation includes diverse model families and sizes, and is supported by robustness checks.We then show that the…

  PublisherOA PDFDOI

• Interrogating LLM design under copyright law

  2025-06-23 · 1 citations

  articleOpen accessSenior author
  PublisherDOI

• Cancer-Myth: Evaluating Large Language Models on Patient Questions with False Presuppositions

  arXiv (Cornell University) · 2025-04-15 · 1 citations

  preprintOpen accessSenior author

  Cancer patients are increasingly turning to large language models (LLMs) for medical information, making it critical to assess how well these models handle complex, personalized questions. However, current medical benchmarks focus on medical exams or consumer-searched questions and do not evaluate LLMs on real patient questions with patient details. In this paper, we first have three hematology-oncology physicians evaluate cancer-related questions drawn from real patients. While LLM responses ar…

  PublisherOA PDFDOI

• Convergent Evolution: How Different Language Models Learn Similar Number Representations

  arXiv (Cornell University) · 2026-04-22

  preprintOpen accessSenior author

  Language models trained on natural text learn to represent numbers using periodic features with dominant periods at $T=2, 5, 10$. In this paper, we identify a two-tiered hierarchy of these features: while Transformers, Linear RNNs, LSTMs, and classical word embeddings trained in different ways all learn features that have period-$T$ spikes in the Fourier domain, only some learn geometrically separable features that can be used to linearly classify a number mod-$T$. To explain this incongruity, w…

  PublisherDOI

• Generating Complex Code Analyzers from Natural Language Questions

  arXiv (Cornell University) · 2026-05-10

  preprintOpen access

  Many software development tasks, such as implementing features and fixing bugs, begin with developers posing questions about a codebase. However, answering questions about codebases that span millions of lines of code across thousands of files is non-trivial. Standard tools like grep cannot answer questions requiring semantic or inter-procedural reasoning, and large language models (LLMs) struggle with large codebases due to resource and context constraints. In this paper, we present Merlin, a n…

  PublisherDOI

Frequent coauthors

• Percy Liang

  33 shared

• Joe Barrow

  25 shared

• Jordan Boyd‐Graber

  25 shared

• John P. Lalor

  25 shared

• Kai-Wei Chang

  25 shared

• Pedro Rodríguez

  25 shared

• Alexander Hoyle

  25 shared

• Sameer Singh

  25 shared

Labs

• Allegro LabPI

  The AI, Language, Learning, Generalization, and Robustness (ALLeGRo) Lab at USC.

Education

• Ph.D., Computer Science

  Stanford University

Awards & honors

• Google ML and Systems Junior Faculty Award
• USC - Capital One Center for Responsible AI and Decision Mak…
• USC-Amazon Center on Secure and Trusted Machine Learning gif…
• Cisco Research award for my research on estimating capabilit…
• Google Research Scholar award for my research on understandi…

Similar researchers at University of Southern California

• Ramesh Govindanh-101
• Jonathan Gratchh-82
• Muhao Chenh-74