Zhenghao Liu

43 papers · 2018–2026 · 9 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (10) 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (7) 🗺️ Taxonomy Completionist (70) 🌉 Interdisciplinary Bridge 🌍 Conference Polyglot (7) 🏃 Academic Marathon (7) 🧭 Keyword Pioneer 🔬 Deep Specialist (10) 🤝 Dynamic Duo (30) 🗃️ Keyword Collector (183) ⚡ Prolific Year (15) 💎 Century Club (39) 🔥 Unstoppable (8)

Conferences

ACL (16) EMNLP (11) ICLR (5) AAAI (3) NAACL (3) COLING (2) EACL (1) IJCAI (1) IJCNLP (1)

Top co-authors

Zhiyuan Liu (32) Maosong Sun (20) Yukun Yan (16) Chenyan Xiong (16) Shuo Wang (13) Ge Yu (12) Shi Yu (10) Xinze Li (8) Xu Han (7) Zheni Zeng (6)

Keywords

large language model (7) retrieval-augmented generation (6) dense retrieval (5) information retrieval (5) chain-of-thought prompting (3) direct preference optimization (3) neural information retrieval (3) code generation (3) supervised fine-tuning (3) language model pretraining (2) personality modeling (2) semantic embedding (2) dialogue system (2) knowledge graph (2) semantic search (2) contrastive learning (2) fact verification (2) preference optimization (2) information extraction (2) evaluation metric (2)

Papers

LexChain: Modeling Legal Reasoning Chains for Chinese Tort Case Analysis AAAI 2026

PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths AAAI 2026

IROTE: Human-like Traits Elicitation of Large Language Model via In-Context Self-Reflective Optimization AAAI 2026

ThinkNote: Enhancing Knowledge Integration and Utilization of Large Language Models via Constructivist Cognition Modeling EACL 2026

PersLLM: A Personified Training Approach for Large Language Models EMNLP 2025

KBAlign: Efficient Self Adaptation on Specific Textual Knowledge Bases EMNLP 2025

ReCUT: Balancing Reasoning Length and Accuracy in LLMs via Stepwise Trails and Preference Optimization EMNLP 2025

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis NAACL 2025

RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework ACL 2025

RankCoT: Refining Knowledge for Retrieval-Augmented Generation through Ranking Chain-of-Thoughts ACL 2025

Judge as A Judge: Improving the Evaluation of Retrieval-Augmented Generation through the Judge-Consistency of Large Language Models ACL 2025

BLCU-ICALL at BEA 2025 Shared Task: Multi-Strategy Evaluation of AI Tutors ACL 2025

Node-Time Conditional Prompt Learning in Dynamic Graphs ICLR 2025

RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards ICLR 2025

Advancing LLM Reasoning Generalists with Preference Trees ICLR 2025

VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents ICLR 2025

DeepNote: Note-Centric Deep Retrieval-Augmented Generation EMNLP 2025

ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation EMNLP 2025

ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance EMNLP 2025

Fusion-in-T5: Unifying Variant Signals for Simple and Effective Document Ranking with Attention Fusion COLING 2024

UltraLink: An Open-Source Knowledge-Enhanced Multilingual Supervised Fine-tuning Dataset ACL 2024

MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin ACL 2024

Cleaner Pretraining Corpus Curation with Neural Web Scraping ACL 2024

INTERVENOR: Prompting the Coding Ability of Large Language Models with the Interactive Chain of Repair ACL 2024

MatPlotAgent: Method and Evaluation for LLM-Based Agentic Scientific Data Visualization ACL 2024

MCTS: A Multi-Reference Chinese Text Simplification Dataset COLING 2024

Enhancing Legal Case Retrieval via Scaling High-quality Synthetic Query-Candidate Pairs EMNLP 2024

Toolink: Linking Toolkit Creation and Using through Chain-of-Solving on Open-Source Model NAACL 2024

Structure-Aware Language Model Pretraining Improves Dense Retrieval on Structured Data ACL 2023

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval ICLR 2023

Leveraging Prefix Transfer for Multi-Intent Text Revision ACL 2023

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder EMNLP 2022

Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision IJCNLP 2021

TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling EMNLP 2021

Neural Quality Estimation with Multiple Hypotheses for Grammatical Error Correction NAACL 2021

Few-Shot Text Ranking with Meta Adapted Synthetic Weak Supervision ACL 2021

Adapting Open Domain Fact Extraction and Verification to COVID-FACT through In-Domain Language Modeling EMNLP 2020

Text Style Transfer via Learning Style Instance Supported Latent Space IJCAI 2020

Fine-grained Fact Verification with Kernel Graph Attention Network ACL 2020

Coreferential Reasoning Learning for Language Representation EMNLP 2020

Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs ACL 2020

DocRED: A Large-Scale Document-Level Relation Extraction Dataset ACL 2019

Entity-Duet Neural Ranking: Understanding the Role of Knowledge Graph Semantics in Neural Information Retrieval ACL 2018