linlu-qiu / lm-inductive-reasoning
☆25Updated 9 months ago
Related projects: ⓘ
- Official code for paper Understanding the Reasoning Ability of Language Models From the Perspective of Reasoning Paths Aggregation☆13Updated 6 months ago
- ☆44Updated 8 months ago
- ☆30Updated 7 months ago
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆78Updated last week
- A Kernel-Based View of Language Model Fine-Tuning https://arxiv.org/abs/2210.05643☆68Updated last year
- Code for Residual Energy-Based Models for Text Generation in PyTorch.☆22Updated 3 years ago
- ☆49Updated last year
- Source codes for "Preference-grounded Token-level Guidance for Language Model Fine-tuning" (NeurIPS 2023).☆12Updated 10 months ago
- ☆25Updated 7 months ago
- ☆25Updated last year
- Directional Preference Alignment☆44Updated 3 months ago
- [EMNLP 2021] Dataset and PyTorch Code for ExplaGraphs: An Explanation Graph Generation Task for Structured Commonsense Reasoning☆10Updated last year
- Implementation of ICML 22 Paper: Scaling Structured Inference with Randomization☆14Updated 2 years ago
- ☆46Updated 10 months ago
- ☆24Updated 4 months ago
- ☆36Updated 5 months ago
- Direct preference optimization with f-divergences.☆11Updated this week
- Code for "Towards Revealing the Mystery behind Chain of Thought: a Theoretical Perspective"☆14Updated last year
- A codebase for ACL 2023 paper: Mitigating Label Biases for In-context Learning☆9Updated last year
- ☆69Updated 10 months ago
- ☆80Updated 9 months ago
- ☆10Updated 3 weeks ago
- ☆70Updated 10 months ago
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆80Updated 3 years ago
- Code for paper "Leakage-Adjusted Simulatability: Can Models Generate Non-Trivial Explanations of Their Behavior in Natural Language?"☆20Updated 3 years ago
- Code for our paper: "GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models"☆50Updated last year
- ☆40Updated last year
- [ICLR 2023] Code for our paper "Selective Annotation Makes Language Models Better Few-Shot Learners"☆105Updated last year
- Code for ACL 2023 paper "BOLT: Fast Energy-based Controlled Text Generation with Tunable Biases".☆17Updated last year
- NumGLUE: A Suite of Fundamental yet Challenging Mathematical Reasoning Tasks☆20Updated 2 years ago