Pengfei He
22 papers · 2022–2026 · 8 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 ↓+6 more ↓ Show less ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (51) π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver π€ Dynamic Duo (15)
ποΈ
Keyword Collector
(100)
β‘
Prolific Year Β· Prolific
π₯
Unstoppable Β· Bronze
β
The Questioner
π
Century Club Β· Bronze
π
Renaissance Researcher
(6)
Top co-authors
Research topics
Artificial Intelligence
(21)
Core AI
(20)
Machine Learning
(14)
Learning Types Β· Machine Learning
(11)
Deep Learning
(7)
Application Areas
(6)
Natural Language Processing
(5)
Learning Types Β· Deep Learning
(5)
Learning Paradigms
(3)
Computer Science
(2)
Applications
(2)
Architectures
(2)
Core Methods
(2)
Generation
(2)
Optimization & Theory
(2)
Keywords
large language model
(10)
retrieval-augmented generation
(4)
multi-agent system
(3)
in-context learning
(3)
language model
(2)
adversarial learning
(2)
training data
(2)
data poisoning
(2)
adversarial attack
(2)
domain adaptation
(2)
few-shot learning
(1)
text classification
(1)
gradient-based optimization
(1)
uncertainty quantification
(1)
sparse coding
(1)
adversarial robustness
(1)
privacy attack
(1)
autoregressive generation
(1)
graph laplacian
(1)
chain-of-thought reasoning
(1)
Papers
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
ACL 2026
PEAR: Planner-Executor Agent Robustness Benchmark
EACL 2026
Retrieval Heads are Dynamic
ACL 2026
SLICEFORMER: Static Program Slicing Using Language Models With Dataflow-Aware Pretraining and Constrained Decoding
ACL 2026
Advancing Reasoning with Off-the-Shelf LLMs: A Semantic Structure Perspective
EMNLP 2025
A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
AISTATS 2025
Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?
EMNLP 2025
Data Poisoning for In-context Learning
NAACL 2025
Mitigating the Privacy Issues in Retrieval-Augmented Generation (RAG) via Pure Synthetic Data
EMNLP 2025
Red-Teaming LLM Multi-Agent Systems via Communication Attacks
ACL 2025
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
ACL 2025
Superiority of Multi-Head Attention: A Theoretical Study in Shallow Transformers in In-Context Linear Regression
AISTATS 2025
Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
ACL 2025
Unveiling Privacy Risks in LLM Agent Memory
ACL 2025
Exploring Memorization in Fine-tuned Language Models
ACL 2024
On the Generalization of Training-based ChatGPT Detection Methods
EMNLP 2024
Sharpness-Aware Data Poisoning Attack
ICLR 2024
The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)
ACL 2024
Towards Understanding Jailbreak Attacks in LLMs: A Representation Space Analysis
EMNLP 2024
Large sample spectral analysis of graph-based multi-manifold clustering
JMLR 2023
Probabilistic Categorical Adversarial Attack and Adversarial Training
ICML 2023
Rainier: Reinforced Knowledge Introspector for Commonsense Question Answering
EMNLP 2022