Reshmi Ghosh
4 papers · 2023–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
๐ Cross-Pollinator (14) ๐ฃ Hot Topic Early Bird ๐ Conference Polyglot (2) ๐ Interdisciplinary Bridge ๐บ๏ธ Taxonomy Completionist (12)
๐งญ
Keyword Pioneer
๐ฅ
Mega-Team
(21)
โ
The Questioner
Conferences
EMNLP (2)
EACL (1)
NIPS (1)
Top co-authors
Keywords
large language model
(2)
fisher information
(1)
adversarial attack
(1)
value alignment
(1)
prompt optimization
(1)
security evaluation
(1)
prompt injection
(1)
language encoder
(1)
defense mechanism
(1)
security vulnerability
(1)
attack success rate
(1)
layer selection
(1)
selective fine-tuning
(1)
reward poisoning
(1)
ethical alignment
(1)
parameter-efficient method
(1)
model defense
(1)
human-ai alignment
(1)
contextual evaluation
(1)
societal value
(1)
Papers
Are My Optimized Prompts Compromised? Exploring Vulnerabilities of LLM-based Optimizers
EACL 2026
ValueCompass: A Framework for Measuring Contextual Value Alignment Between Human and LLMs
EMNLP 2025
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
NIPS 2024
On Surgical Fine-tuning for Language Encoders
EMNLP 2023