alonj / Same-Task-More-Tokens
The code for the paper: "Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models"
☆45Updated 2 months ago
Related projects: ⓘ
- Official code for "MAmmoTH2: Scaling Instructions from the Web"☆106Updated this week
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning"☆87Updated 2 months ago
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆72Updated 8 months ago
- ☆52Updated 7 months ago
- Official repository for "Scaling Retrieval-Based Langauge Models with a Trillion-Token Datastore".☆81Updated 2 weeks ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆182Updated last month
- Official implementation for the paper "LongEmbed: Extending Embedding Models for Long Context Retrieval"☆108Updated 4 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆39Updated 7 months ago
- ☆118Updated 5 months ago
- MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents☆55Updated this week
- Official repository for paper "Weak-to-Strong Extrapolation Expedites Alignment"☆62Updated 3 months ago
- LOFT: A 1 Million+ Token Long-Context Benchmark☆127Updated 2 weeks ago
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆89Updated 4 months ago
- Official github repo for the paper "Compression Represents Intelligence Linearly"☆121Updated 3 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆127Updated 2 weeks ago
- open-source code for paper: Retrieval Head Mechanistically Explains Long-Context Factuality☆135Updated last month
- BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval☆41Updated last month
- FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions☆37Updated 2 months ago
- Scripts for generating synthetic finetuning data for reducing sycophancy.☆105Updated last year
- Small and Efficient Mathematical Reasoning LLMs☆69Updated 7 months ago
- Self-Alignment with Principle-Following Reward Models☆144Updated 6 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆44Updated 8 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆195Updated 3 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆96Updated last week
- Source code of "Reasons to Reject? Aligning Language Models with Judgments"☆54Updated 6 months ago
- ☆105Updated this week
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆65Updated last month
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆72Updated 4 months ago
- Unofficial implementation of AlpaGasus☆83Updated 11 months ago
- Reformatted Alignment☆111Updated 4 months ago