Search papers, labs, and topics across Lattice.
City University of Hong Kong
5
1
5
10
FunReason-MT is presented, a novel data synthesis framework for real-world multi-turn tool use that resolves the complexity barrier in multi-turn FC data by employing 1) Environment-API Graph Interactions to gather varied high-quality trajectories, 2) Advanced Tool-Query Synthesis to simplify hard query construction, and 3) Guided Iterative Chain for sophisticated CoT generation.
Stop relying on LLMs to "hallucinate" reasoning paths – SEARCH-R uses a fine-tuned Llama3.1-8B model and dependency tree-based retrieval to navigate multi-hop question answering more reliably.
LLMs can now reliably extract job skills from text, even in low-resource settings, thanks to a novel framework that enforces output validity and reduces hallucinations.
Memory dilution in LLMs is tackled head-on with a novel framework that not only preserves information but also amplifies reasoning capabilities.
Forget random sampling – this framework crafts targeted, multi-turn function-calling data that catapults smaller LLMs to state-of-the-art performance.
