Generating Training Data with Language Models: Towards Zero-Shot Language Understanding
Paper • 2202.04538 • Published
Jiaxin Huang
teapot123
AI & ML interests
None yet
Recent Activity
authored a paper 4 days ago
Generating Training Data with Language Models: Towards Zero-Shot
Language Understanding authored a paper 4 days ago
Efficient Test-Time Scaling via Self-Calibration authored a paper 4 days ago
CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs
with Controllable Puzzle GenerationOrganizations
authored 13
papers 4 days ago
Efficient Test-Time Scaling via Self-Calibration
Paper • 2503.00031 • Published • 15
CrossWordBench: Evaluating the Reasoning Capabilities of LLMs and LVLMs with Controllable Puzzle Generation
Paper • 2504.00043 • Published • 10
POSS: Position Specialist Generates Better Draft for Speculative Decoding
Paper • 2506.03566 • Published • 6
R-Zero: Self-Evolving Reasoning LLM from Zero Data
Paper • 2508.05004 • Published • 131
VisPlay: Self-Evolving Vision-Language Models from Images
Paper • 2511.15661 • Published • 44
RelayLLM: Efficient Reasoning via Collaborative Decoding
Paper • 2601.05167 • Published • 31
Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
Paper • 2602.03845 • Published • 27
Training Data Efficiency in Multimodal Process Reward Models
Paper • 2602.04145 • Published • 79
Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
Paper • 2602.03689 • Published
Text Classification Using Label Names Only: A Language Model Self-Training Approach
Paper • 2010.07245 • Published
Nonsense Helps: Prompt Space Perturbation Broadens Reasoning Exploration
Paper • 2605.05566 • Published • 37
G-Zero: Self-Play for Open-Ended Generation from Zero Data
Paper • 2605.09959 • Published • 16
authored 5
papers over 1 year ago
Large Language Models Can Self-Improve
Paper • 2210.11610 • Published
Tuning Language Models as Training Data Generators for Augmentation-Enhanced Few-Shot Learning
Paper • 2211.03044 • Published • 1
Optimizing Language Model's Reasoning Abilities with Weak Supervision
Paper • 2405.04086 • Published • 2
Taming Overconfidence in LLMs: Reward Calibration in RLHF
Paper • 2410.09724 • Published • 3
Divide, Reweight, and Conquer: A Logit Arithmetic Approach for In-Context Learning
Paper • 2410.10074 • Published • 1