microsoft / deep-language-networks
We view Large Language Models as stochastic language layers in a network, where the learnable parameters are the natural language prompts at each layer. We stack two such layers, feeding the output of one layer to the next. We call the stacked architecture a Deep Language Network - DLN
☆92Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for deep-language-networks
- Building modular LMs with parameter-efficient fine-tuning.☆83Updated this week
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆48Updated 7 months ago
- SILO Language Models code repository☆80Updated 8 months ago
- This repository includes code for the paper "Does Localization Inform Editing? Surprising Differences in Where Knowledge Is Stored vs. Ca…☆55Updated last year
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆109Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆62Updated 5 months ago
- RL algorithm: Advantage induced policy alignment☆62Updated last year
- The GitHub repo for Goal Driven Discovery of Distributional Differences via Language Descriptions☆68Updated last year
- ☆112Updated last month
- Code of ICLR paper: https://openreview.net/forum?id=-cqvvvb-NkI☆91Updated last year
- Scalable Meta-Evaluation of LLMs as Evaluators☆41Updated 9 months ago
- A repository for transformer critique learning and generation☆86Updated 11 months ago
- Reproduction of "RLCD Reinforcement Learning from Contrast Distillation for Language Model Alignment☆65Updated last year
- Language models scale reliably with over-training and on downstream tasks☆94Updated 7 months ago
- Skill-It! A Data-Driven Skills Framework for Understanding and Training Language Models☆41Updated last year
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆73Updated 3 months ago
- [EMNLP'23] Execution-Based Evaluation for Open Domain Code Generation☆44Updated 10 months ago
- Self-Alignment with Principle-Following Reward Models☆147Updated 8 months ago
- ☆33Updated last year
- A framework for few-shot evaluation of autoregressive language models.☆101Updated last year
- ☆38Updated 7 months ago
- [ACL'24] Code and data of paper "When is Tree Search Useful for LLM Planning? It Depends on the Discriminator"☆49Updated 8 months ago
- ☆24Updated 4 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆108Updated 2 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆129Updated this week
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆44Updated 10 months ago
- A unified benchmark for math reasoning☆87Updated last year
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆62Updated last year
- This project studies the performance and robustness of language models and task-adaptation methods.☆141Updated 6 months ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆155Updated 6 months ago