Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?

• URL: http://arxiv.org/abs/2406.12307v3
• Date: Tue, 17 Dec 2024 05:33:04 GMT
• Title: Can Tool-augmented Large Language Models be Aware of Incomplete Conditions?
• Authors: Seungbin Yang, ChaeHun Park, Taehee Kim, Jaegul Choo,
• Abstract summary: This study examines whether large language models can identify incomplete conditions and appropriately determine when to refrain from using tools. Our experiments show that LLMs often struggle to identify the absence of information required to utilize specific tools. Our research can contribute to advancing reliable LLMs by addressing common scenarios during interactions between humans and LLMs.
• Score: 33.74511128798095
• License:
• Abstract: Recent advancements in integrating large language models (LLMs) with tools have allowed the models to interact with real-world environments. However, these tool-augmented LLMs often encounter incomplete scenarios when users provide partial information or the necessary tools are unavailable. Recognizing and managing such scenarios is crucial for LLMs to ensure their reliability, but this exploration remains understudied. This study examines whether LLMs can identify incomplete conditions and appropriately determine when to refrain from using tools. To this end, we address a dataset by manipulating instances from two datasets by removing necessary tools or essential information for tool invocation. Our experiments show that LLMs often struggle to identify the absence of information required to utilize specific tools and recognize the absence of appropriate tools. We further analyze model behaviors in different environments and compare their performance against humans. Our research can contribute to advancing reliable LLMs by addressing common scenarios during interactions between humans and LLMs. Our code and dataset will be publicly available.

Related papers

• Adaptive Tool Use in Large Language Models with Meta-Cognition Trigger [49.81945268343162]
  We propose MeCo, an adaptive decision-making strategy for external tool use. MeCo captures high-level cognitive signals in the representation space, guiding when to invoke tools. Our experiments show that MeCo accurately detects LLMs' internal cognitive signals and significantly improves tool-use decision-making.
  arXiv  Detail & Related papers  (2025-02-18T15:45:01Z)
• Self-Training Large Language Models for Tool-Use Without Demonstrations [15.17750971071501]
  Large language models (LLMs) remain prone to factual inaccuracies and computational errors. Recent work augmented LLMs with tools to mitigate these shortcomings, but often requires curated gold tool-use demonstrations. This paper investigates whether LLMs can learn to use tools without demonstrations.
  arXiv  Detail & Related papers  (2025-02-09T12:06:10Z)
• Tool Unlearning for Tool-Augmented LLMs [14.755831733659699]
  Tool-augmented large language models (LLMs) are often trained on datasets of query-response pairs. ToolDelete is the first approach for unlearning tools from tool-augmented LLMs.
  arXiv  Detail & Related papers  (2025-02-03T05:50:55Z)
• Learning to Ask: When LLM Agents Meet Unclear Instruction [55.65312637965779]
  Large language models (LLMs) can leverage external tools for addressing a range of tasks unattainable through language skills alone. We evaluate the performance of LLMs tool-use under imperfect instructions, analyze the error patterns, and build a challenging tool-use benchmark called Noisy ToolBench. We propose a novel framework, Ask-when-Needed (AwN), which prompts LLMs to ask questions to users whenever they encounter obstacles due to unclear instructions.
  arXiv  Detail & Related papers  (2024-08-31T23:06:12Z)
• WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models [31.742620965039517]
  Large Language Models (LLMs) excel in NLP tasks, but still need external tools to extend their ability. We introduce the Whether-or-not tool usage Evaluation benchmark (WTU-Eval) to assess LLMs with eleven datasets. The results of eight LLMs on WTU-Eval reveal that LLMs frequently struggle to determine tool use in general datasets. Fine-tuning Llama2-7B results in a 14% average performance improvement and a 16.8% decrease in incorrect tool usage.
  arXiv  Detail & Related papers  (2024-07-02T12:07:38Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)
• Towards Practical Tool Usage for Continually Learning LLMs [28.62382804829694]
  Large language models show an innate skill for solving language based tasks. But their knowledge, stored directly within their parameters, remains static in time. Tool use helps by offloading work to systems that the LLM can access through an interface. But LLMs that use them still must adapt to nonstationary environments for prolonged use.
  arXiv  Detail & Related papers  (2024-04-14T19:45:47Z)
• LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error [54.954211216847135]
  Existing large language models (LLMs) only reach a correctness rate in the range of 30% to 60%. We propose a biologically inspired method for tool-augmented LLMs, simulated trial and error (STE) STE orchestrates three key mechanisms for successful tool use behaviors in the biological system: trial and error, imagination, and memory.
  arXiv  Detail & Related papers  (2024-03-07T18:50:51Z)
• ToolEyes: Fine-Grained Evaluation for Tool Learning Capabilities of Large Language Models in Real-world Scenarios [49.33633818046644]
  We propose ToolEyes, a fine-grained system tailored for the evaluation of large language models' tool learning capabilities in authentic scenarios. The system meticulously examines seven real-world scenarios, analyzing five dimensions crucial to LLMs in tool learning. ToolEyes incorporates a tool library boasting approximately 600 tools, serving as an intermediary between LLMs and the physical world.
  arXiv  Detail & Related papers  (2024-01-01T12:49:36Z)
• MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use [79.87054552116443]
  Large language models (LLMs) have garnered significant attention due to their impressive natural language processing (NLP) capabilities. We introduce MetaTool, a benchmark designed to evaluate whether LLMs have tool usage awareness and can correctly choose tools. We conduct experiments involving eight popular LLMs and find that the majority of them still struggle to effectively select tools.
  arXiv  Detail & Related papers  (2023-10-04T19:39:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.