Agastya Seth — accepted AI-conference papers

2025

UnSeenTimeQA: Time-Sensitive Question-Answering Beyond LLMs’ Memorization

Md Nayem Uddin, Amir Saeidi, Divij Handa, Agastya Seth, Tran Cao Son, Eduardo Blanco +2

ACL 2025long

This paper introduces UnSeenTimeQA, a novel data contamination-free time-sensitive question-answering (TSQA) benchmark. It differs from existing TSQA benchmarks by avoiding web-searchable queries grounded in the real world. We present a series of time-sensitive event scenarios based on synthetically…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness

Neeraj Varshney, Pavel Dolin, Agastya Seth, Chitta Baral

ACL 2024findings

As Large Language Models (LLMs) play an increasingly pivotal role in natural language processing applications, their safety concerns become critical areas of NLP research. This has resulted in the development of various LLM defense strategies. Unfortunately, despite the shared goal of improving the…

Cited by 43 Source ↗PDF ↗code ↗Scholar ↗