uq-project / UQLinks
UQ: Assessing Language Models on Unsolved Questions
☆23Updated last week
Alternatives and similar repositories for UQ
Users that are interested in UQ are comparing it to the libraries listed below
Sorting:
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆60Updated last year
- ☆67Updated 5 months ago
- ☆26Updated 2 months ago
- ☆40Updated 3 months ago
- Code for RATIONALYST: Pre-training Process-Supervision for Improving Reasoning https://arxiv.org/pdf/2410.01044☆35Updated 11 months ago
- The original Shared Recurrent Memory Transformer implementation☆30Updated last month
- ☆49Updated 11 months ago
- ☆24Updated 3 months ago
- Leveraging Base Language Models for Few-Shot Synthetic Data Generation☆33Updated last month
- The code implementation of MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models…☆36Updated last year
- ☆23Updated 3 weeks ago
- Official code repository for the paper "ToMAP: Training Opponent-Aware LLM Persuaders with Theory of Mind"☆14Updated 3 months ago
- Verifiers for LLM Reinforcement Learning☆71Updated 4 months ago
- Multi-Agent Verification: Scaling Test-Time Compute with Multiple Verifiers☆20Updated 6 months ago
- Official repository for "BLEUBERI: BLEU is a surprisingly effective reward for instruction following"☆25Updated 2 months ago
- Resa: Transparent Reasoning Models via SAEs☆41Updated 3 weeks ago
- Source code for the collaborative reasoner research project at Meta FAIR.☆103Updated 4 months ago
- ☆54Updated 9 months ago
- KV Cache Steering for Inducing Reasoning in Small Language Models☆39Updated last month
- ☆23Updated 11 months ago
- Aioli: A unified optimization framework for language model data mixing☆27Updated 7 months ago
- NeurIPS 2023 - Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer☆43Updated last year
- Fork of Flame repo for training of some new stuff in development☆17Updated last week
- The official implementation for paper "Agentic-R1: Distilled Dual-Strategy Reasoning"☆94Updated this week
- ☆48Updated 3 months ago
- ReBase: Training Task Experts through Retrieval Based Distillation☆29Updated 6 months ago
- Analysis code for paper "SciArena: An Open Evaluation Platform for Foundation Models in Scientific Literature Tasks"☆49Updated 3 weeks ago
- ☆19Updated 3 weeks ago
- accompanying material for sleep-time compute paper☆107Updated 4 months ago
- BigOBench assesses the capacity of Large Language Models (LLMs) to comprehend time-space computational complexity of input or generated c…☆37Updated 4 months ago