alonj / Same-Task-More-TokensLinks
The code for the paper: "Same Task, More Tokens: the Impact of Input Length on the Reasoning Performance of Large Language Models"
☆54Updated last year
Alternatives and similar repositories for Same-Task-More-Tokens
Users that are interested in Same-Task-More-Tokens are comparing it to the libraries listed below
Sorting:
- Code and Data for "Long-context LLMs Struggle with Long In-context Learning" [TMLR2025]☆108Updated 7 months ago
- A dataset of LLM-generated chain-of-thought steps annotated with mistake location.☆82Updated last year
- Official code for "MAmmoTH2: Scaling Instructions from the Web" [NeurIPS 2024]☆148Updated 11 months ago
- Benchmarking LLMs with Challenging Tasks from Real Users☆241Updated 11 months ago
- [ICLR'25] Data and code for our paper "Why Does the Effective Context Length of LLMs Fall Short?"☆77Updated 10 months ago
- Official github repo for the paper "Compression Represents Intelligence Linearly" [COLM 2024]☆141Updated last year
- LongEmbed: Extending Embedding Models for Long Context Retrieval (EMNLP 2024)☆143Updated 10 months ago
- [NeurIPS 2024] OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI☆105Updated 7 months ago
- PASTA: Post-hoc Attention Steering for LLMs☆123Updated 10 months ago
- Official repository for ACL 2025 paper "Model Extrapolation Expedites Alignment"☆75Updated 4 months ago
- 🚢 Data Toolkit for Sailor Language Models☆94Updated 7 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆59Updated last year
- ☆52Updated last year
- Replicating O1 inference-time scaling laws☆90Updated 10 months ago
- ☆127Updated last year
- ☆73Updated 6 months ago
- The HELMET Benchmark☆172Updated last month
- Self-Alignment with Principle-Following Reward Models☆165Updated 2 weeks ago
- ☆84Updated 8 months ago
- ☆74Updated last year
- ☆136Updated 10 months ago
- Official implementation for "Law of the Weakest Link: Cross capabilities of Large Language Models"☆42Updated last year
- ☆72Updated last year
- [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples☆106Updated 2 months ago
- [ACL 2025 Findings] Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts (As Huggingface Daily Papers: …☆86Updated last month
- Official implementation for 'Extending LLMs’ Context Window with 100 Samples'☆80Updated last year
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆64Updated 5 months ago
- Reformatted Alignment☆113Updated last year
- ☆39Updated 6 months ago
- Scalable Meta-Evaluation of LLMs as Evaluators☆42Updated last year