open-source llms
Open-source language models (LLMs) are large language models made publicly available for research and development, allowing researchers and developers to modify, study, and utilize these models without proprietary restrictions.
- Analogy-based Multi-Turn Jailbreak against Large Language Models
- Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks
- Fairshare Data Pricing via Data Valuation for Large Language Models
- On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection
- PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QA
- Token Embeddings Violate the Manifold Hypothesis
- When Can Model-Free Reinforcement Learning be Enough for Thinking?