Search Results for author:
Found 9 papers, 6 papers with code
StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Models
The virtual API server contains a caching system and API simulators which are complementary to alleviate the change in API status.
RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation
Generative models have demonstrated considerable potential in software engineering, particularly in tasks such as code generation and debugging.
Investigate-Consolidate-Exploit: A General Strategy for Inter-Task Agent Self-Evolution
This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution.
QASnowball: An Iterative Bootstrapping Framework for High-Quality Question-Answering Data Generation
Recent years have witnessed the success of question answering (QA), especially its potential to be a foundation paradigm for tackling diverse NLP tasks.
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
Based on ToolBench, we fine-tune LLaMA to obtain an LLM ToolLLaMA, and equip it with a neural API retriever to recommend appropriate APIs for each instruction.
Ranked #3 on
Trajectory Planning
on ToolBench
Exploring Format Consistency for Instruction Tuning
Instruction tuning has emerged as a promising approach to enhancing large language models in following human instructions.
WebCPM: Interactive Web Search for Chinese Long-form Question Answering
We recruit annotators to search for relevant information using our interface and then answer questions.
Tool Learning with Foundation Models
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
Bi-Link: Bridging Inductive Link Predictions from Text via Contrastive Learning of Transformers and Prompts
In our experiments, Bi-Link outperforms recent baselines on link prediction datasets (WN18RR, FB15K-237, and Wikidata5M).
