paper-with-me

홈 › Papers

Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option

2024-10-15 · Konstantin Yakovlev, Sergey Nikolenko, Andrey Bout

The recently proposed ToolkenGPT tool learning paradigm demonstrates promising performance but suffers from two major issues: first, it cannot benefit from tool documentation, and second, it often makes mistakes in whether to use a tool at all. We introduce Toolken+ that mitigates the first problem by reranking top $k$ tools selected by ToolkenGPT and the second problem with a special "Reject" option such that the model will generate a vocabulary token if "Reject" is ranked first. We demonstrate the effectiveness of Toolken+ on multistep numerical reasoning and tool selection tasks.

📄 PDF Abstract BibTeX arXiv:2410.12004

Code (0)

등록된 구현이 없습니다.

Tasks

Reranking

Similar Papers 제목 키워드 기반

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

2023-05-19 · NeurIPS 2023 11 · Shibo Hao, Tianyang Liu, Zhen Wang, Zhiting Hu

Augmenting large language models (LLMs) with external tools has emerged as a promising approach to solving complex problems. However, traditional methods, which finetune LLMs with tool demonstration data, can be both cos…

In-Context LearningQuestion Answering

AI Receptivity or AI Adoption Breadth? A Tool-Specific Reanalysis of the Lower-Literacy/Higher-Usage Link

2026-06-11 · Hristo Inouzhe arxiv

Recent evidence reported by Tully, Longoni, and Appel (2025) suggests that lower artificial intelligence (AI) literacy predicts greater receptivity toward AI. We revisit this claim using the public data from Study 3 of t…

On Reject and Refine Options in Multicategory Classification

2017-01-09 · Chong Zhang, Wenbo Wang, Xingye Qiao

In many real applications of statistical learning, a decision made from misclassification can be too costly to afford; in this case, a reject option, which defers the decision until further investigation is conducted, is…

Binary ClassificationClassificationGeneral ClassificationLearning Theory

Stacked Confusion Reject Plots (SCORE)

2024-06-25 · Stephan Hasler, Lydia Fischer

Machine learning is more and more applied in critical application areas like health and driver assistance. To minimize the risk of wrong decisions, in such applications it is necessary to consider the certainty of a clas…

Regression with reject option and application to kNN

2020-06-30 · NeurIPS 2020 12 · Christophe Denis, Mohamed Hebiri, Ahmed Zaoui

We investigate the problem of regression where one is allowed to abstain from predicting. We refer to this framework as regression with reject option as an extension of classification with reject option. In this context,…

regression