Chirag Agarwal's picture

4 3

Chirag Agarwal

AikyamLab

·

https://chirag-agarwall.github.io/

AI & ML interests

Explainability and Interpretability; AI Safety; AI Alignment

Recent Activity

upvoted a paper about 1 month ago

CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare

upvoted a paper about 1 month ago

Polarity-Aware Probing for Quantifying Latent Alignment in Language Models

liked a dataset about 1 month ago

SabrinaSadiekh/not_hate_dataset

View all activity

Organizations

upvoted 2 papers about 1 month ago

CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare

Paper • 2512.11437 • Published Dec 12, 2025 • 3

Polarity-Aware Probing for Quantifying Latent Alignment in Language Models

Paper • 2511.21737 • Published Nov 21, 2025 • 1

upvoted a collection about 1 month ago

Polarity-Aware Probing Datasets

Datasets for PA-Probing described in "Polarity-Aware Probing for Quantifying Latent Alignment in Language Models" https://www.arxiv.org/pdf/2511.21737 • 2 items • Updated Dec 7, 2025 • 1

upvoted a paper almost 2 years ago

Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models

Paper • 2402.04614 • Published Feb 7, 2024 • 3