wenzhe-li / Self-MoALinks
☆18Updated 4 months ago
Alternatives and similar repositories for Self-MoA
Users that are interested in Self-MoA are comparing it to the libraries listed below
Sorting:
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- Self-Supervised Alignment with Mutual Information☆19Updated last year
- Evaluate the Quality of Critique☆35Updated last year
- ☆18Updated 11 months ago
- Offcial Repo of Paper "Eliminating Position Bias of Language Models: A Mechanistic Approach""☆14Updated 9 months ago
- Lightweight Adapting for Black-Box Large Language Models☆22Updated last year
- Exploration of automated dataset selection approaches at large scales.☆42Updated 3 months ago
- ☆45Updated 3 months ago
- ☆19Updated 10 months ago
- Official implementation of AAAI 2025 paper "Augmenting Math Word Problems via Iterative Question Composing"(https://arxiv.org/abs/2401.09…☆20Updated 5 months ago
- ☆16Updated 4 months ago
- ☆14Updated last year
- ☆32Updated 4 months ago
- ☆17Updated last month
- Code for Paper (Preserving Diversity in Supervised Fine-tuning of Large Language Models)☆24Updated 3 weeks ago
- ☆18Updated last year
- What Makes a Reward Model a Good Teacher? An Optimization Perspective☆31Updated last month
- [ACL 2024] Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models☆21Updated 10 months ago
- Learning from preferences is a common paradigm for fine-tuning language models. Yet, many algorithmic design decisions come into play. Ou…☆29Updated last year
- Code for "Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining"☆16Updated last month
- Code for "Reasoning to Learn from Latent Thoughts"☆104Updated 2 months ago
- Unofficial Implementation of Chain-of-Thought Reasoning Without Prompting☆32Updated last year
- ICML 2024 - Official Repository for EXO: Towards Efficient Exact Optimization of Language Model Alignment☆55Updated 11 months ago
- official implementation of ICLR'2025 paper: Rethinking Bradley-Terry Models in Preference-based Reward Modeling: Foundations, Theory, and…☆58Updated 2 months ago
- ☆75Updated 3 weeks ago
- [ICLR 2025] "Training LMs on Synthetic Edit Sequences Improves Code Synthesis" (Piterbarg, Pinto, Fergus)☆19Updated 3 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆54Updated last year
- Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision☆120Updated 8 months ago
- ☆25Updated 9 months ago
- Efficient Scaling laws and collaborative pretraining.☆16Updated 4 months ago