likenneth / persona_drift
Measuring and Controlling Persona Drift in Language Model Dialogs
☆12Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for persona_drift
- ☆28Updated 7 months ago
- Critique-out-Loud Reward Models☆37Updated last month
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆41Updated 10 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- Repository containing the SPIN experiments on the DIBT 10k ranked prompts☆23Updated 8 months ago
- ☆27Updated 5 months ago
- Codebase for Instruction Following without Instruction Tuning☆32Updated last month
- ☆31Updated 10 months ago
- IntructIR, a novel benchmark specifically designed to evaluate the instruction following ability in information retrieval models. Our foc…☆28Updated 5 months ago
- A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.☆76Updated 9 months ago
- [NeurIPS 2024] Train LLMs with diverse system messages reflecting individualized preferences to generalize to unseen system messages☆37Updated last month
- Repository for Skill Set Optimization☆12Updated 3 months ago
- Demonstration that finetuning RoPE model on larger sequences than the pre-trained model adapts the model context limit☆63Updated last year
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Updated 9 months ago
- ☆22Updated 2 weeks ago
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions☆40Updated 4 months ago
- Minimal implementation of the Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models paper (ArXiv 20232401.01335)☆28Updated 8 months ago
- Code for the examples presented in the talk "Training a Llama in your backyard: fine-tuning very large models on consumer hardware" given…☆14Updated last year
- Repository for "I am a Strange Dataset: Metalinguistic Tests for Language Models"☆39Updated 10 months ago
- ☆38Updated 7 months ago
- ☆37Updated last year
- Code and data from the paper 'Human Feedback is not Gold Standard'☆18Updated 4 months ago
- This is a new metric that can be used to evaluate faithfulness of text generated by LLMs. The work behind this repository can be found he…☆31Updated last year
- PyTorch code for System-1.x: Learning to Balance Fast and Slow Planning with Language Models☆20Updated 4 months ago
- ☆32Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆19Updated 2 months ago
- Plug-and-play Search Interfaces with Pyserini and Hugging Face☆32Updated last year
- ☆41Updated 2 weeks ago
- ☆56Updated 9 months ago