Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
Paper • 2506.02132 • Published • 1
Nishant Subramani
nsubramani23
AI & ML interests
NLP, Machine Learning, Text Generation
Recent Activity
authored a paper about 14 hours ago
Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models authored a paper about 14 hours ago
LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization authored a paper about 14 hours ago
SimBA: Simplifying Benchmark Analysis Using Performance Matrices AloneOrganizations
authored 12
papers about 14 hours ago
LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization
Paper • 2510.04013 • Published • 1
SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone
Paper • 2510.17998 • Published • 1
Personal Information Parroting in Language Models
Paper • 2602.20580 • Published • 1
Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion
Paper • 2604.16656 • Published • 1
How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
Paper • 2605.08348 • Published • 1
On the Persistent Effects of Lexicality in Large Language Models
Paper • 2606.02750 • Published
The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
Paper • 2606.07822 • Published • 1
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
Paper • 2607.00083 • Published • 1
Learning from 53.6K Real-World Developer Edits of AI-Generated Code
Paper • 2607.25130 • Published
Cross-modal Steering Vectors Exist Across Both Image and Text Generation
Paper • 2610.36269 • Published • 8
MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
Paper • 2504.20168 • Published • 1
upvoted 8
papers about 20 hours ago
Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
Paper • 2506.02132 • Published • 1
LLM Microscope: What Model Internals Reveal About Answer Correctness and Context Utilization
Paper • 2510.04013 • Published • 1
SimBA: Simplifying Benchmark Analysis Using Performance Matrices Alone
Paper • 2510.17998 • Published • 1
Personal Information Parroting in Language Models
Paper • 2602.20580 • Published • 1
Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion
Paper • 2604.16656 • Published • 1
How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits
Paper • 2605.08348 • Published • 1
The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust
Paper • 2606.07822 • Published • 1
Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust
Paper • 2607.00083 • Published • 1