whyNLP / Conic10K
Conic10K: A large-scale dataset for closed-vocabulary math problem understanding. Accepted to EMNLP2023 Findings.
☆23Updated 9 months ago
Related projects: ⓘ
- [ICLR'24 spotlight] Tool-Augmented Reward Modeling☆33Updated 6 months ago
- GSM-Plus: Data, Code, and Evaluation for Enhancing Robust Mathematical Reasoning in Math Word Problems.☆38Updated 2 months ago
- ☆31Updated 5 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆31Updated 5 months ago
- [ACL 2023] Solving Math Word Problems via Cooperative Reasoning induced Language Models☆33Updated 9 months ago
- Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".☆22Updated 5 months ago
- ☆23Updated 2 months ago
- Domain-specific preference (DSP) data and customized RM fine-tuning.☆24Updated 6 months ago
- Benchmarking Benchmark Leakage in Large Language Models☆39Updated 4 months ago
- the instructions and demonstrations for building a formal logical reasoning capable GLM☆49Updated 2 weeks ago
- ☆80Updated 9 months ago
- ☆16Updated 6 months ago
- [ACL 2023 Findings] What In-Context Learning “Learns” In-Context: Disentangling Task Recognition and Task Learning☆21Updated last year
- [ACL 2024 Findings] CriticBench: Benchmarking LLMs for Critique-Correct Reasoning☆20Updated 6 months ago
- ☆25Updated 7 months ago
- Evaluate the Quality of Critique☆35Updated 3 months ago
- Directional Preference Alignment☆44Updated 3 months ago
- [ACL 2024] Self-Training with Direct Preference Optimization Improves Chain-of-Thought Reasoning