Sarthak Jain
22 papers · 2015–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+8 more ↓ Show less ↑
🏃 Academic Marathon (10) 🧭 Keyword Pioneer 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (6) 🐝 Cross-Pollinator (5)
🏃
Academic Marathon
(10)
🧭
Keyword Pioneer
🐝
Cross-Pollinator
(5)
🔬
Deep Specialist
(10)
🔥
Unstoppable
(8)
💎
Century Club
(22)
❓
The Questioner
(2)
🗃️
Keyword Collector
(95)
Conferences
NAACL (7)
ACL (5)
EMNLP (5)
INTERSPEECH (3)
AISTATS (1)
EACL (1)
Top co-authors
Keywords
influence function
(3)
named entity recognition
(3)
relation extraction
(3)
attention mechanism
(3)
disentangled representation
(2)
rationale extraction
(2)
feature importance
(2)
text classification
(2)
large language model
(2)
model interpretability
(2)
speaker recognition
(2)
self-supervised learning
(2)
model explanation
(2)
instance attribution
(2)
question answering
(1)
model robustness
(1)
document-level extraction
(1)
video generation
(1)
variational inference
(1)
part-of-speech tagging
(1)
Papers
Aligning to Constraints for Data-Efficient Language Model Customization
NAACL 2025
ViBe: A Text-to-Video Benchmark for Evaluating Hallucination in Large Multimodal Models
NAACL 2025
MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models
EMNLP 2024
PERSONA: an application for emotion recognition, gender recognition and age estimation
INTERSPEECH 2024
ComFeAT: combination of neural and spectral features for improved depression detection
INTERSPEECH 2024
The reasonable effectiveness of speaker embeddings for violence detection
INTERSPEECH 2024
How Many and Which Training Points Would Need to be Removed to Flip this Prediction?
EACL 2023
Influence Functions for Sequence Tagging Models
EMNLP 2022
Combining Feature and Instance Attribution to Detect Artifacts
ACL 2022
An Empirical Comparison of Instance Attribution Methods for NLP
NAACL 2021
Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?
NAACL 2021
Modular Self-Supervision for Document-Level Relation Extraction
EMNLP 2021
Learning to Faithfully Rationalize by Construction
ACL 2020
ERASER: A Benchmark to Evaluate Rationalized NLP Models
ACL 2020
SciREX: A Challenge Dataset for Document-Level Information Extraction
ACL 2020
SUPP.AI: finding evidence for supplement-drug interactions
ACL 2020
Attention is not Explanation
NAACL 2019
An Analysis of Attention over Clinical Notes for Predictive Tasks
NAACL 2019
Structured Disentangled Representations
AISTATS 2019
Learning Disentangled Representations of Texts with Application to Biomedical Abstracts
EMNLP 2018
Question Answering over Knowledge Base using Factual Memory Networks
NAACL 2016
Cross Lingual Sentiment Analysis using Modified BRAE
EMNLP 2015