centerforaisafety / emergent-values
Code for "Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs"
☆46Updated last month
Alternatives and similar repositories for emergent-values:
Users that are interested in emergent-values are comparing it to the libraries listed below
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆55Updated 7 months ago
- Functional Benchmarks and the Reasoning Gap☆85Updated 6 months ago
- ☆48Updated 5 months ago
- An example implementation of RLHF (or, more accurately, RLAIF) built on MLX and HuggingFace.☆25Updated 10 months ago
- ☆50Updated 5 months ago
- [ACL 2024] Do Large Language Models Latently Perform Multi-Hop Reasoning?☆63Updated last month
- ☆20Updated last year
- accompany material for sleep time compute paper☆17Updated last week
- ☆51Updated last week
- ☆48Updated last year
- Implementation of the paper: "AssistantBench: Can Web Agents Solve Realistic and Time-Consuming Tasks?"☆54Updated 4 months ago
- EMNLP 2024 "Re-reading improves reasoning in large language models". Simply repeating the question to get bidirectional understanding for…☆25Updated 4 months ago
- A framework for pitting LLMs against each other in an evolving library of games ⚔☆33Updated last week
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆41Updated last week
- look how they massacred my boy☆63Updated 6 months ago
- Official repo for the paper PHUDGE: Phi-3 as Scalable Judge. Evaluate your LLMs with or without custom rubric, reference answer, absolute…☆49Updated 9 months ago
- The first dense retrieval model that can be prompted like an LM☆71Updated 7 months ago
- Systematic evaluation framework that automatically rates overthinking behavior in large language models.☆86Updated 2 weeks ago
- An introduction to LLM Sampling☆77Updated 4 months ago
- Mixing Language Models with Self-Verification and Meta-Verification☆104Updated 4 months ago
- QAlign is a new test-time alignment approach that improves language model performance by using Markov chain Monte Carlo methods.☆22Updated 2 weeks ago
- Code and data for the paper "Why think step by step? Reasoning emerges from the locality of experience"☆60Updated 3 weeks ago
- Evaluating LLMs with CommonGen-Lite☆89Updated last year
- Simple examples using Argilla tools to build AI☆52Updated 5 months ago
- ☆20Updated last month
- ☆18Updated 6 months ago
- Optimizing Causal LMs through GRPO with weighted reward functions and automated hyperparameter tuning using Optuna☆39Updated 2 months ago
- ☆40Updated 11 months ago
- Just a bunch of benchmark logs for different LLMs☆119Updated 8 months ago
- A fast, local, and secure approach for training LLMs for coding tasks using GRPO with WebAssembly and interpreter feedback.☆22Updated 3 weeks ago