update.

section6/section6.tex

@@ -198,7 +198,7 @@ With such data, SFT teaches the model to imitate the demonstrated tool-use patte
 
 
 A common way to construct such data is to manually annotate tool-use trajectories. However, this requires annotators to know which tool should be used, how to write valid arguments, and how to judge whether the returned observation is useful. This process is costly and difficult to scale to many tools and tasks.
 A common way to construct such data is to manually annotate tool-use trajectories. However, this requires annotators to know which tool should be used, how to write valid arguments, and how to judge whether the returned observation is useful. This process is costly and difficult to scale to many tools and tasks.
 
 
-Toolformer addresses this data construction problem with a self-supervised approach \citep{schick-etal:toolformer}. Instead of relying on large-scale human annotations, it starts from only a few demonstrations for each API. It then lets the language model annotate a large text corpus with possible API calls. After executing these calls, Toolformer keeps only the API calls that help the model better predict future tokens. In this way, the model can automatically construct useful tool-use training data. The filtered data is then used to fine-tune the model. This process teaches the model to decide when to call a tool, what arguments to pass, and how to incorporate the tool result into later generation.
+A representative approach to addressing this data construction problem is Toolformer, which uses a self-supervised method to generate tool-use data \citep{schick-etal:toolformer}. Instead of relying on large-scale human annotations, Toolformer starts from only a few demonstrations for each API. It then lets the language model annotate a large text corpus with possible API calls. After executing these calls, Toolformer keeps only the API calls that help the model better predict future tokens. The filtered data is then used to fine-tune the model. Through this process, the model learns when to call a tool, what arguments to pass, and how to incorporate the tool result into later generation.
 
 
 Beyond learning to use a small set of tools, later studies further scale tool-use training to larger and more realistic API spaces. API-Bank builds a benchmark and training set for tool-augmented LLMs, where models need to plan, retrieve, and call APIs in executable environments \citep{li-etal:apibank}. ToolLLM constructs ToolBench with more than 16,000 real-world APIs and uses automatically generated instruction-solution trajectories to train ToolLLaMA \citep{qin-etal:toolllm}. Gorilla focuses on API calling at scale and fine-tunes LLaMA-based models to generate accurate API calls. It also uses a document retriever to reduce API hallucination and adapt to changing API documents \citep{patil-etal:gorilla}.
 Beyond learning to use a small set of tools, later studies further scale tool-use training to larger and more realistic API spaces. API-Bank builds a benchmark and training set for tool-augmented LLMs, where models need to plan, retrieve, and call APIs in executable environments \citep{li-etal:apibank}. ToolLLM constructs ToolBench with more than 16,000 real-world APIs and uses automatically generated instruction-solution trajectories to train ToolLLaMA \citep{qin-etal:toolllm}. Gorilla focuses on API calling at scale and fine-tunes LLaMA-based models to generate accurate API calls. It also uses a document retriever to reduce API hallucination and adapt to changing API documents \citep{patil-etal:gorilla}.
 
 
@@ -209,6 +209,7 @@ Beyond learning to use a small set of tools, later studies further scale tool-us
 
 
 
 
 
 
+
 % 5. Efficient Tool Use
 % 5. Efficient Tool Use
 \subsubsubsection{Efficient Tool Use}
 \subsubsubsection{Efficient Tool Use}