maxwellreuter / chatgpt-refusals
Datasets and code from our paper, where we use machine learning to predict if ChatGPT will refuse a given prompt.
☆36Updated last year
Alternatives and similar repositories for chatgpt-refusals:
Users that are interested in chatgpt-refusals are comparing it to the libraries listed below
- Official repo for NAACL 2024 Findings paper "LeTI: Learning to Generate from Textual Interactions."☆63Updated last year
- Functional Benchmarks and the Reasoning Gap☆84Updated 6 months ago
- a pipeline for using api calls to agnostically convert unstructured data into structured training data☆30Updated 6 months ago
- Just a bunch of benchmark logs for different LLMs☆119Updated 8 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- ☆22Updated last year
- ☆24Updated last year
- Score LLM pretraining data with classifiers☆55Updated last year
- Search through Facebook Research's PyTorch BigGraph Wikidata-dataset with the Weaviate vector search engine☆31Updated 3 years ago
- Multi-Domain Expert Learning☆67Updated last year
- Based on the tree of thoughts paper☆47Updated last year
- ☆48Updated last year
- A repository of projects and datasets under active development by Alignment Lab AI☆22Updated last year
- A library for squeakily cleaning and filtering language datasets.☆46Updated last year
- 📝 Reference-Free automatic summarization evaluation with potential hallucination detection☆100Updated last year
- ☆84Updated last year
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆25Updated 9 months ago
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆24Updated last year
- Zeus LLM Trainer is a rewrite of Stanford Alpaca aiming to be the trainer for all Large Language Models☆69Updated last year
- Visualize expert firing frequencies across sentences in the Mixtral MoE model☆17Updated last year
- ☆38Updated last month
- Simple replication of [ColBERT-v1](https://arxiv.org/abs/2004.12832).☆80Updated last year
- assign color hues to a collection of text fragments based on embeddings☆20Updated 9 months ago
- ☆13Updated last month
- Using open source LLMs to build synthetic datasets for direct preference optimization☆59Updated last year
- ☆57Updated 6 months ago
- Track the progress of LLM context utilisation☆54Updated 8 months ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- ☆20Updated last month
- Data preparation code for Amber 7B LLM☆86Updated 10 months ago