Makesh Narsimhan Sreedhar
11 papers · 2020–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (36) π Interdisciplinary Bridge π Conference Polyglot (4)
π
Academic Marathon
(5)
π
Cross-Pollinator
(12)
π
Century Club
(11)
ποΈ
Keyword Collector
(55)
Conferences
EMNLP (5)
ACL (3)
NAACL (2)
NIPS (1)
Top co-authors
Keywords
large language model
(4)
dialogue system
(4)
adversarial learning
(2)
language model
(2)
canonical form
(2)
content moderation
(2)
preference learning
(2)
ai safety
(2)
domain adaptation
(1)
neural machine translation
(1)
model security
(1)
multilingual translation
(1)
task-oriented dialogue
(1)
intent classification
(1)
question answering
(1)
few-shot learning
(1)
model alignment
(1)
cross-lingual transfer
(1)
human feedback
(1)
prompt learning
(1)
Papers
Guardrails and Security for LLMs: Safe, Secure and Controllable Steering of LLM Applications
ACL 2025
AEGIS2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails
NAACL 2025
Safety Through Reasoning: An Empirical Study of Reasoning Guardrail Models
EMNLP 2025
HelpSteer 2: Open-source dataset for training top-performing reward models
NIPS 2024
Unsupervised Extraction of Dialogue Policies from Conversations
EMNLP 2024
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
NAACL 2024
NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails
EMNLP 2023
Local Byte Fusion for Neural Machine Translation
ACL 2023
Single Sequence Prediction over Reasoning Graphs for Multi-hop QA
ACL 2023
Prompt Learning for Domain Adaptation in Task-Oriented Dialogue
EMNLP 2022
Learning Improvised Chatbots from Adversarial Modifications of Natural Language Feedback
EMNLP 2020