Jingheng Pan
3 papers · 2024–2025 · 2 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 · Bronze
Top co-authors
Research topics
Keywords
sentiment analysis
(1)
multimodal learning
(1)
language model
(1)
parameter-efficient fine-tuning
(1)
vision-language model
(1)
hallucination mitigation
(1)
multimodal fusion
(1)
sentiment polarity
(1)
chinese language processing
(1)
controlled text generation
(1)
chinese language
(1)
text rewriting
(1)
contrastive decoding
(1)
toxic language
(1)
toxic language detection
(1)
model steering
(1)
large language model
(1)
layer intervention
(1)
cognitive indicator
(1)
Papers
Chinese Toxic Language Mitigation via Sentiment Polarity Consistent Rewrites
EMNLP 2025
CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
ACL 2025
Mitigating Hallucinations in Large Vision-Language Models with Instruction Contrastive Decoding
ACL 2024