Zhengliang Shi
14 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 ↓+5 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (36) 🏆 Keyword Champion (5)
🧭
Keyword Pioneer
🤝
Dynamic Duo
(10)
🗃️
Keyword Collector
(66)
💎
Century Club · Bronze
⚡
Prolific Year · Productive
Top co-authors
Research topics
Artificial Intelligence
(9)
Machine Learning
(9)
Core AI
(9)
Deep Learning
(7)
Natural Language Processing
(7)
Learning Types · Machine Learning
(6)
Applications
(5)
Generation
(5)
Learning Types · Deep Learning
(5)
Application Areas
(4)
Resources & Methods
(4)
Learning Paradigms
(2)
Models
(2)
Speech & Audio
(1)
Optimization & Theory
(1)
Keywords
large language model
(6)
tool learning
(5)
language model
(4)
information retrieval
(3)
contrastive learning
(2)
instruction tuning
(2)
benchmark evaluation
(2)
dense retrieval
(2)
preference alignment
(1)
preference optimization
(1)
knowledge distillation
(1)
modality alignment
(1)
response generation
(1)
self-supervised learning
(1)
autonomous agent
(1)
natural language generation
(1)
iterative learning
(1)
language model agent
(1)
supervised fine-tuning
(1)
in-context learning
(1)
Papers
BatonVoice: An Operationalist Framework for Enhancing Controllable Speech Synthesis with Linguistic Intelligence from LLMs
ACL 2026
Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent Systems
EMNLP 2025
Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation
ACL 2025
Mitigating Hallucinations in Large Vision-Language Models via Entity-Centric Multimodal Preference Optimization
EMNLP 2025
Retrieval Models Aren’t Tool-Savvy: Benchmarking Tool Retrieval for Large Language Models
ACL 2025
TTPA: Token-level Tool-use Preference Alignment Training Framework with Fine-grained Evaluation
EMNLP 2025
360∘REA: Towards A Reusable Experience Accumulation with 360∘ Assessment for Multi-Agent System
ACL 2024
Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult Curriculum
AAAI 2024
Generate-then-Ground in Retrieval-Augmented Generation for Multi-hop Question Answering
ACL 2024
Learning to Use Tools via Cooperative and Interactive Agents
EMNLP 2024
MAIR: A Massive Benchmark for Evaluating Instructed Retrieval
EMNLP 2024
Contrastive Learning Reduces Hallucination in Conversations
AAAI 2023
RADE: Reference-Assisted Dialogue Evaluation for Open-Domain Dialogue
ACL 2023
Towards a Unified Framework for Reference Retrieval and Related Work Generation
EMNLP 2023