Daben Liu
10 papers · 2017–2026 · 5 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (25) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver ⚡ Prolific Year · Productive
💎
Century Club · Bronze
🗃️
Keyword Collector
(57)
Top co-authors
Research topics
Artificial Intelligence
(7)
Machine Learning
(6)
Natural Language Processing
(6)
Applications
(6)
Core AI
(6)
Learning Types · Machine Learning
(4)
Deep Learning
(2)
Application Areas
(2)
Learning Paradigms
(2)
Models
(2)
Optimization & Theory · Machine Learning
(2)
Resources & Methods
(2)
Core Methods
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
retrieval-augmented generation
(6)
uncertainty quantification
(3)
question answering
(2)
model robustness
(1)
model merging
(1)
fact verification
(1)
embedding learning
(1)
acoustic model
(1)
information retrieval
(1)
readability assessment
(1)
human judgment
(1)
sequence classification
(1)
synthetic data generation
(1)
fault detection
(1)
perturbation analysis
(1)
speech recognition
(1)
model calibration
(1)
generative model
(1)
deep neural network
(1)
human perception
(1)
Papers
DF-RAG: Query-Aware Diversity for Retrieval-Augmented Generation
EACL 2026
RAFFLES: Reasoning-based Attribution of Faults for LLM Systems
EACL 2026
A Comparison of Independent and Joint Fine-tuning Strategies for Retrieval-Augmented Generation
EMNLP 2025
An Automatic Method to Estimate Correctness of RAG
COLING 2025
Confidence-Based Response Abstinence: Improving LLM Trustworthiness via Activation-Based Uncertainty Estimation
EMNLP 2025
FB-RAG: Improving RAG with Forward and Backward Lookup
IJCNLP 2025
Harmonizing Diverse Models: A Layer-wise Merging Strategy for Consistent Generation
EMNLP 2025
Readability Reconsidered A Cross-Dataset Analysis of Reference-Free Metrics
EMNLP 2025
TruthTorchLM: A Comprehensive Library for Predicting Truthfulness in LLM Outputs
EMNLP 2025
Improving DNN Bluetooth Narrowband Acoustic Models by Cross-Bandwidth and Cross-Lingual Initialization
Interspeech 2017