
Yash Kumar Lal
PhD Student @ Stony Brook University
evaluation
llm
causal knowledge
transformers
nlp
computational social science
summarization
entailment
natural language generation
gpt-3
qa
large language models
commonsense reasoning
zero shot
question answering
13
presentations
5
number of views
SHORT BIO
Yash Kumar Lal is a PhD candidate at Stony Brook University advised by Niranjan Balasubramanian. He is interested in understanding various aspects of narratives and procedures using the lens of why questions. He is also interested in investigating and improving the personalization abilities of LLMs.
Presentations

CaT-Bench: Benchmarking Language Model Understanding of Causal and Temporal Dependencies in Plans
Yash Kumar Lal and 4 other authors

Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization
Yash Kumar Lal and 5 other authors

Automated Adversarial Discovery for Safety Classifiers
Yash Kumar Lal and 4 other authors

SOCIALITE-LLAMA: An Instruction-Tuned Model for Social Scientific Tasks
Gourab Dey and 8 other authors

SAGEViz: SchemA GEneration and Visualization
Sugam Devare and 11 other authors

Systematic Evaluation of GPT-3 for Zero-Shot Personality Estimation
Adithya V Ganesan and 1 other author

Evaluating Paraphrastic Robustness in Textual Entailment Models
Dhruv Verma and 4 other authors

Using Commonsense Knowledge to Answer Why-Questions
Yash Kumar Lal and 6 other authors

Analyzing the Contribution of Commonsense Knowledge for Why-Question Answering
Yash Kumar Lal and 5 other authors

IrEne-viz: Visualizing Energy Consumption of Transformer Models
Yash Kumar Lal and 5 other authors

TellMeWhy: A Dataset for Answering Why-Questions in Narratives
Yash Kumar Lal and 3 other authors

IrEne: Interpretable Energy Prediction for Transformers
Qingqing Cao and 4 other authors

TellMeWhy: A Dataset for Answering Why-Questions in Narratives
Yash Kumar Lal and 3 other authors