collaborators

6 papers

cs.AI2026

Understanding Annotator Safety Policy with Interpretability

Alex Oesterling, Donghao Ren, Yannick Assogba +4

Safety policies define what constitutes safe and unsafe AI outputs, guiding data annotation and model development. However, annotation disagreement is pervasive and can stem from m…

cs.CL2026

Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language

Angie Boggust, Donghao Ren, Yannick Assogba +3

Automated interpretability aims to translate large language model (LLM) features into human understandable descriptions. However, natural language feature descriptions can be vague…

cs.CL2025

Constructive Circuit Amplification: Improving Math Reasoning in LLMs via Targeted Sub-Network Updates

Nikhil Prakash, Donghao Ren, Dominik Moritz +1

Prior studies investigating the internal workings of LLMs have uncovered sparse subnetworks, often referred to as circuits, that are responsible for performing specific tasks. Addi…

cs.CV2025

EncQA: Benchmarking Vision-Language Models on Visual Encodings for Charts

Kushin Mukherjee, Donghao Ren, Dominik Moritz +1

Multimodal vision-language models (VLMs) continue to achieve ever-improving scores on chart understanding benchmarks. Yet, we find that this progress does not fully capture the bre…

cs.CL2025

Evaluating Long Range Dependency Handling in Code Generation LLMs

Yannick Assogba, Donghao Ren

As language models support larger and larger context sizes, evaluating their ability to make effective use of that context becomes increasingly important. We analyze the ability of…

cs.HC2025

Exploring Empty Spaces: Human-in-the-Loop Data Augmentation

Catherine Yeh, Donghao Ren, Yannick Assogba +2

Data augmentation is crucial to make machine learning models more robust and safe. However, augmenting data can be challenging as it requires generating diverse data points to rigo…