Sunhao Dai
9 papers · 2024–2026 · 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 · Gold 🗺️ Taxonomy Completionist (31) ⚡ Prolific Year · Productive 🌈 Renaissance Researcher (5)
🗃️
Keyword Collector
(53)
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(7)
Core AI
(6)
Natural Language Processing
(5)
Applications · Natural Language Processing
(4)
Resources & Methods
(4)
Learning Types
(3)
Application Areas
(2)
Core Methods
(2)
Optimization & Theory
(2)
Computer Science
(1)
Data Science & Analytics
(1)
Deep Learning
(1)
Interdisciplinary
(1)
Applications · Computer Science
(1)
Keywords
large language model
(4)
information retrieval
(2)
retrieval-augmented generation
(2)
source bia
(2)
transfer learning
(1)
knowledge distillation
(1)
benchmark evaluation
(1)
document retrieval
(1)
online learning
(1)
out-of-distribution generalization
(1)
document ranking
(1)
batch learning
(1)
distribution shift
(1)
trial and error
(1)
language model
(1)
bipartite matching
(1)
contextual bandit
(1)
text embedding
(1)
credit assignment
(1)
bandit setting
(1)
Papers
MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
ACL 2026
AdaO2B: Adaptive Online to Batch Conversion for Out-of-Distribution Generalization
AAAI 2025
CitaLaw: Enhancing LLM with Citations in Legal Domain
ACL 2025
From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions
ICLR 2025
Length-Induced Embedding Collapse in PLM-based Models
ACL 2025
Media Source Matters More Than Content: Unveiling Political Bias in LLM-Generated Citations
EMNLP 2025
Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents
ICLR 2025
Uplift-RAG: Uplift-Driven Knowledge Preference Alignment for Retrieval-Augmented Generation
EMNLP 2025
Cocktail: A Comprehensive Information Retrieval Benchmark with LLM-Generated Documents Integration
ACL 2024