Xiaozhi Wang
- Papers
- 16
Cite
Notes
Only stored in your browser.
Authored papers
16WildReward: Learning Reward Models from In-the-Wild Human Interactions
arXiv 2026
VerIF: Verification Engineering for Reinforcement Learning in Instruction Following
arXiv 2025
AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic Scenarios
arXiv 2025
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
arXiv 2025
LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitasks
arXiv 2024
Constraint Back-translation Improves Complex Instruction Following of Large Language Models
arXiv 2024
ADELIE: Aligning Large Language Models on Information Extraction
arXiv 2024
Language-Specific Representation of Emotion-Concept Knowledge Causally Supports Emotion Inference
arXiv 2023
GOAL: A Challenging Knowledge-grounded Video Captioning Benchmark for Real-time Soccer Commentary Generation
arXiv 2023
MAVEN-Arg: Completing the Puzzle of All-in-One Event Understanding Dataset with Event Argument Annotation
arXiv 2023
ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time
arXiv 2023
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
arXiv 2023
COPEN: Probing Conceptual Knowledge in Pre-trained Language Models
arXiv 2022
Sub-Character Tokenization for Chinese Pretrained Language Models
arXiv 2021
CPM: A Large-scale Generative Chinese Pre-trained Language Model
arXiv 2020
KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation
arXiv 2019
Affiliations
Frequent co-authors
10from 16 papers