Ranjan Satapathy
8 papers · 2024–2026 · 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 · Silver
🗺️
Taxonomy Completionist
(13)
❓
The Questioner
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Natural Language Processing
(5)
Resources & Methods
(4)
Deep Learning
(2)
Machine Learning
(2)
Learning Types · Machine Learning
(2)
Knowledge & Reasoning
(1)
Applications
(1)
Architectures
(1)
Core Methods
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Reasoning
(1)
Keywords
large language model
(4)
causal mediation
(2)
sparse autoencoder
(2)
refusal behavior
(2)
chain-of-thought reasoning
(1)
text generation
(1)
interpretable machine learning
(1)
model interpretability
(1)
mechanistic interpretability
(1)
jailbreak attack
(1)
hallucination reduction
(1)
model interpretation
(1)
natural language explanation
(1)
activation patching
(1)
feature intervention
(1)
sustainability reporting
(1)
faithfulness measurement
(1)
causal faithfulness
(1)
environmental social governance
(1)
extractive rationalization
(1)
Papers
Beyond I’m Sorry, I Can’t: Dissecting Large-Language-Model Refusal
AAAI 2026
From Earnings Calls to Investment Reports: Evaluating Role-based Multi-Agent LLM Systems
EMNLP 2025
SusGen-GPT: A Data-Centric LLM for Financial NLP and Sustainability Report Generation
NAACL 2025
Towards Faithful Natural Language Explanations: A Study Using Activation Patching in Large Language Models
EMNLP 2025
Understanding Refusal in Language Models with Sparse Autoencoders
EMNLP 2025
How Interpretable are Reasoning Explanations from Prompting Large Language Models?
NAACL 2024
Plausible Extractive Rationalization through Semi-Supervised Entailment Signal
ACL 2024
Self-training Large Language Models through Knowledge Detection
EMNLP 2024