FIRE: Flexible Integration of Data Quality Ratings for Effective Pre-Training
arxiv, Feb 2025
Publications
You can also find my articles on my Google Scholar profile.
Preprints
Hellobench: Evaluating long text generation capabilities of large language models
arxiv, Sep 2024
Knowledge-driven cot: Exploring faithful reasoning in llms for knowledge-intensive question answering
arxiv, Aug 2023
Conference Papers
Enhancing LLMs via High-Knowledge Data Selection
AAAI 2025, Apr 2025
FRAMES: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
ACL 2025 Findings, Feb 2025
Preference curriculum: Llms should always be pretrained on their preferred data
ACL 2025 Findings, Jan 2025
D-cpt law: Domain-specific continual pre-training scaling law for large language models
NeuIPS 2024, Dec 2024
PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness
EMNLP 2024 Findings, Oct 2024
Generative Spoken Language Modeling with Quantized Feature Enhancement
IJCNN 2024, Jun 2024
Llms know what they need: Leveraging a missing information guided framework to empower retrieval-augmented generation
CoLing 2025, Apr 2024