paper-with-me

Papers

Improving Small-Scale Large Language Models Function Calling for Reasoning Tasks

2024-10-24 · Graziano A. Manduzio, Federico A. Galatolo, Mario G. C. A. Cimino, Enzo Pasquale Scilingo, Lorenzo Cominelli

Recent advancements in Large Language Models (LLMs) have demonstrated exceptional capabilities in natural language understanding and generation. While these models excel in general complex reasoning tasks, they still face challenges in mathematical problem-solving and logical reasoning. To address these limitations, researchers have explored function calling abilities, allowing LLMs to execute provided functions and utilize their outputs for task completion. However, concentrating on specific tasks can be very inefficient for large-scale LLMs to be used, because of the expensive cost of training and inference stages they need in terms of computational resources. This study introduces a novel framework for training smaller language models in function calling, focusing on specific logical and mathematical reasoning tasks. The approach aims to improve performances of small-scale models for these tasks using function calling, ensuring a high level of accuracy. Our framework employs an agent that, given a problem and a set of callable functions, queries the LLM by injecting a description and examples of the usable functions into the prompt and managing their calls in a step-by-step reasoning chain. This process is used to create a dataset of correct and incorrect reasoning chain chat completions from a large-scale LLM. This dataset is used to train a smaller LLM using Reinforcement Learning from Human Feedback (RLHF), specifically employing the Direct Preference Optimization (DPO) technique. Experimental results demonstrate how the proposed approach balances the trade-off between model size and performance, improving the ability of function calling for reasoning tasks, in smaller models.

📄 PDF Abstract BibTeX arXiv:2410.18890

Code (0)

등록된 구현이 없습니다.

Tasks

Logical ReasoningMathematical Problem-SolvingMathematical ReasoningNatural Language Understanding

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Benchmarking Floworks against OpenAI & Anthropic: A Novel Framework for Enhanced LLM Function Calling

2024-10-23 · Nirav Bhan, Shival Gupta, Sai Manaswini, Ritik Baba 외

Large Language Models (LLMs) have shown remarkable capabilities in various domains, yet their economic impact has been limited by challenges in tool use and function calling. This paper introduces ThorV2, a novel archite…

Benchmarking

TinyAgent: Function Calling at the Edge

2024-09-01 · Lutfi Eren Erdogan, Nicholas Lee, Siddharth Jha, Sehoon Kim 외

Recent large language models (LLMs) have enabled the development of advanced agentic systems that can integrate various tools and APIs to fulfill user queries through function calling. However, the deployment of these LL…

Language ModellingQuantizationSmall Language Model

ODIA: Oriented Distillation for Inline Acceleration of LLM-based Function Calling

2025-07-10 · Hanlong Zhang, Jingsheng Yang, Hao Li, Yuhao He 외 arxiv

Function Calling is a crucial technique that enables Large Language Models (LLMs) to interact with external systems through APIs. However, the high latency associated with LLM-based Function Calling significantly impacts…

Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training

2025-02-10 · Yuchen Zhuang, Jingfeng Yang, Haoming Jiang, Xin Liu 외

Due to the scarcity of agent-oriented pre-training data, LLM-based autonomous agents typically rely on complex prompting or extensive fine-tuning, which often fails to introduce new capabilities while preserving strong g…

FunReason: Enhancing Large Language Models' Function Calling via Self-Refinement Multiscale Loss and Automated Data Refinement

2025-05-26 · Bingguang Hao, Maolin Wang, Zengzhuang Xu, Cunyin Peng 외

The integration of large language models (LLMs) with function calling has emerged as a crucial capability for enhancing their practical utility in real-world applications. However, effectively combining reasoning process…