Reshmi Ghosh
4 papers · 2023–2026 · 3 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad
❓
The Questioner
Venues
Top co-authors
Research topics
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
NeurIPS 2024
On Surgical Fine-tuning for Language Encoders
EMNLP 2023