neulab / gemini-benchmark
☆150Updated last year
Alternatives and similar repositories for gemini-benchmark:
Users that are interested in gemini-benchmark are comparing it to the libraries listed below
- ☆119Updated 6 months ago
- Self-Alignment with Principle-Following Reward Models☆158Updated last year
- Code and example data for the paper: Rule Based Rewards for Language Model Safety☆185Updated 8 months ago
- Evaluating LLMs with fewer examples☆150Updated last year
- LOFT: A 1 Million+ Token Long-Context Benchmark☆186Updated last week
- This is the repo for the paper Shepherd -- A Critic for Language Model Generation☆218Updated last year
- RuLES: a benchmark for evaluating rule-following in language models☆220Updated last month
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆105Updated last month
- ☆126Updated 5 months ago
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆80Updated 8 months ago
- The Official Repository for "Bring Your Own Data! Self-Supervised Evaluation for Large Language Models"☆108Updated last year
- Scripts for generating synthetic finetuning data for reducing sycophancy.☆109Updated last year
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆137Updated 5 months ago
- Code and data accompanying our paper on arXiv "Faithful Chain-of-Thought Reasoning".☆157Updated 11 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆205Updated 10 months ago
- The dataset and code for paper: TheoremQA: A Theorem-driven Question Answering dataset☆157Updated 11 months ago
- SILO Language Models code repository☆81Updated last year
- PASTA: Post-hoc Attention Steering for LLMs☆113Updated 4 months ago
- Simple next-token-prediction for RLHF☆224Updated last year
- Code for the paper "Rethinking Benchmark and Contamination for Language Models with Rephrased Samples"☆300Updated last year
- Benchmarking LLMs with Challenging Tasks from Real Users☆221Updated 5 months ago
- ModuleFormer is a MoE-based architecture that includes two different types of experts: stick-breaking attention heads and feedforward exp…☆217Updated last year
- ☆145Updated last year
- ☆164Updated last month
- ☆96Updated 9 months ago
- A simple GPT-based evaluation tool for multi-aspect, interpretable assessment of LLMs.☆85Updated last year
- LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)☆133Updated 5 months ago
- 🚢 Data Toolkit for Sailor Language Models☆88Updated last month
- This is the official repository for Inheritune.☆111Updated 2 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆196Updated last week