Guangliang Liu
10 papers · 2022–2025 · 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 ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (19) 🐣 Hot Topic Early Bird 💎 Century Club · Bronze
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Artificial Intelligence
(10)
Core AI
(8)
Machine Learning
(5)
Natural Language Processing
(5)
Learning Types · Machine Learning
(3)
Application Areas
(2)
Generation
(2)
Learning Paradigms
(2)
Resources & Methods
(2)
Deep Learning
(1)
Applications
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory
(1)
Understanding
(1)
Keywords
large language model
(4)
moral self-correction
(4)
ai safety
(2)
moral reasoning
(2)
few-shot learning
(2)
pre-trained language model
(2)
prompt engineering
(1)
in-context learning
(1)
curriculum learning
(1)
harmful content
(1)
safety alignment
(1)
generalization ability
(1)
distributional semantics
(1)
generalization bound
(1)
hidden state analysis
(1)
data augmentation
(1)
skill learning
(1)
instruction following
(1)
model training
(1)
hidden state
(1)
Papers
A Survey to Recent Progress Towards Understanding In-Context Learning
NAACL 2025
Diagnosing Moral Reasoning Acquisition in Language Models: Pragmatics and Generalization
EMNLP 2025
Discourse Heuristics For Paradoxically Moral Self-Correction
EMNLP 2025
Moral Self-correction is Not An Innate Capability in Language Models
IJCNLP 2025
On the Convergence of Moral Self-Correction in Large Language Models
IJCNLP 2025
Smaller Large Language Models Can Do Moral Self-Correction
NAACL 2025
Intrinsic Self-correction for Enhanced Morality: An Analysis of Internal Mechanisms and the Superficial Hypothesis
EMNLP 2024
Towards Understanding Task-agnostic Debiasing Through the Lenses of Intrinsic Bias and Forgetfulness
ACL 2024
PAC-tuning: Fine-tuning Pre-trained Language Models with PAC-driven Perturbed Gradient Descent
EMNLP 2023
Dynamic Augmentation Data Selection for Few-shot Text Classification
EMNLP 2022