activity
20192026
most citedThe GEM Benchmark: Natural Language Generation, its Evaluation and Metrics

52 citations · 82 across the 13 of their papers we have counts for

collaborators
Showing cs.CLShow all

17 papers · 1 filter

cs.CL2026

Harnessing the Latent Space: From Steering Vectors to Model Calibrators for Control and Trust

Nishant Subramani

Language models have changed from unreliable text generators to highly-capable large models with trillions of parameters. Capability increases come hand-in-hand with increases in s…

cs.CL2026

The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust

Nishant Subramani, Palash Goyal, Yiwen Song +4

As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good proxy for trust: well-calibrated c…

cs.CL2026

On the Persistent Effects of Lexicality in Large Language Models

Hammad Rizwan, Muhammad Umair Haider, Nishant Subramani +3

Representations extracted from large language models (LLMs) play an important role in many downstream applications. However, the structure of these representations is often influen…

cs.CL2026

How Much Do Circuits Tell Us? Measuring the Consistency and Specificity of Language Model Circuits

Michael Li, Nishant Subramani

The circuits framework in mechanistic interpretability aims to identify sparse subgraphs of model components that are causally responsible for a behavior, typically evaluated by me…

cs.CL2026

Defragmenting Language Models: An Interpretability-based Approach for Vocabulary Expansion

Maitrey Mehta, Nishant Subramani, Zhichao Xu +2

All languages are equal; when it comes to tokenization, some are more equal than others. Tokens are the hidden currency that dictate the cost and latency of access to contemporary…

cs.CL2026

Personal Information Parroting in Language Models

Nishant Subramani, Kshitish Ghate, Mona Diab

Modern language models (LM) are trained on large scrapes of the Web, containing millions of personal information (PI) instances, many of which LMs memorize, increasing privacy risk…