Sarkar Snigdha Sarathi Das
8 papers · 2022–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(21)
❓
The Questioner
(2)
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(7)
Core AI · Artificial Intelligence
(7)
Natural Language Processing
(4)
Learning Types · Machine Learning
(4)
Deep Learning
(3)
Optimization & Theory
(3)
Models
(2)
Resources & Methods
(2)
Computer Vision
(1)
Analysis
(1)
Core AI · Computer Vision
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Understanding
(1)
Keywords
large language model
(4)
prompt optimization
(2)
benchmark evaluation
(1)
domain generalization
(1)
domain adaptation
(1)
sequence labeling
(1)
gradient-based optimization
(1)
dialogue state tracking
(1)
uncertainty quantification
(1)
object detection
(1)
question answering
(1)
model evaluation
(1)
response generation
(1)
named entity recognition
(1)
model safety
(1)
scene understanding
(1)
harmful content
(1)
token classification
(1)
parameter efficient
(1)
few-shot learning
(1)
Papers
Can LLMs Rank the Harmfulness of Smaller LLMs? We are Not There Yet
ACL 2025
Demystify Verbosity Compensation Behavior of Large Language Models
EMNLP 2025
GReaTer: Gradients Over Reasoning Makes Smaller Language Models Strong Prompt Optimizers
ICLR 2025
GreaterPrompt: A Unified, Customizable, and High-Performing Open-Source Toolkit for Prompt Optimization
ACL 2025
HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?
ICCV 2025
S3-DST: Structured Open-Domain Dialogue Segmentation and State Tracking in the Era of LLMs
ACL 2024
Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning
EMNLP 2023
CONTaiNER: Few-Shot Named Entity Recognition via Contrastive Learning
ACL 2022