{"url":"/dataset/diaforge-utc-r-0725","name":"diaforge-utc-r-0725","full_name":"DiaFORGE UTC: Unified Tool-Calling Conversations Dataset","description_markdown":"Dataset for our paper Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky which includes 5000 enterprise tools and the corresponding dialogues generated using DiaFORGE UTC data engine.\r\n\r\nThe dataset is generated with the data generation engine. The engine simulates a user agent and an assistant agent in a dialogue, where the user agent has a persona and the assistant agent has access to a set of tools. Detailed information about the data generation process can be found in the paper.\r\n\r\nEach entry in the dataset contains:\r\n- seed: Gold tool for the generated dialogue.\r\n- user_persona: Persona of the simulated user agent.\r\n- messages: List of messages in the dialogue, where each message is a dictionary containing:\r\n- distractor_tools: List of distractor tools that are not the gold tool but are relevant to the dialogue. These tools are used by user agent to generate utterances that are hard to disambiguate from the gold tool.\r\n- retrieved_tools: List of tools retrieved by the assistant agent and used by the assistant agent in order to ask clarifying questions to the user agent.","description_withheld":null,"homepage":"https://huggingface.co/datasets/sap-ai-research/diaforge-utc-r-0725","introduced_date":"2025-07-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/disambiguation-centric-finetuning-makes","title":"Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky","first_author":"Ashutosh Hathidara","url":null},"license":{"name":"CC BY-NC-SA","url":"https://spdx.org/licenses/CC-BY-NC-SA-4.0"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Dialog","url":"/datasets/modality/dialog"},{"name":"Actions","url":"/datasets/modality/actions"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"},{"name":"Intent Detection","url":"/task/intent-detection","datasets_with_task":"/datasets/task/intent-detection"},{"name":"Large Language Model","url":"/task/large-language-model","datasets_with_task":"/datasets/task/large-language-model"},{"name":"Slot Filling","url":"/task/slot-filling","datasets_with_task":"/datasets/task/slot-filling"},{"name":"Entity Resolution","url":"/task/entity-resolution","datasets_with_task":"/datasets/task/entity-resolution"},{"name":"Dialogue Generation","url":"/task/dialogue-generation","datasets_with_task":"/datasets/task/dialogue-generation"},{"name":"Question Generation","url":"/task/question-generation","datasets_with_task":"/datasets/task/question-generation"},{"name":"Entity Disambiguation","url":"/task/entity-disambiguation","datasets_with_task":"/datasets/task/entity-disambiguation"},{"name":"Self-Supervised Learning","url":"/task/self-supervised-learning","datasets_with_task":"/datasets/task/self-supervised-learning"},{"name":"Dialogue State Tracking","url":"/task/dialogue-state-tracking","datasets_with_task":"/datasets/task/dialogue-state-tracking"},{"name":"Task-Oriented Dialogue Systems","url":"/task/task-oriented-dialogue-systems","datasets_with_task":"/datasets/task/task-oriented-dialogue-systems"},{"name":"Synthetic Data Generation","url":"/task/synthetic-data-generation","datasets_with_task":"/datasets/task/synthetic-data-generation"},{"name":"Intent Classification","url":"/task/intent-classification","datasets_with_task":"/datasets/task/intent-classification"},{"name":"Intent Recognition","url":"/task/intent-recognition","datasets_with_task":"/datasets/task/intent-recognition"},{"name":"Intent Discovery","url":"/task/intent-discovery","datasets_with_task":"/datasets/task/intent-discovery"},{"name":"Dialogue Evaluation","url":"/task/dialogue-evaluation","datasets_with_task":"/datasets/task/dialogue-evaluation"},{"name":"Intent Classification and Slot Filling","url":"/task/intent-classification-and-slot-filling","datasets_with_task":"/datasets/task/intent-classification-and-slot-filling"},{"name":"Text2text Generation","url":"/task/text2text-generation-1","datasets_with_task":"/datasets/task/text2text-generation-1"},{"name":"Conversational Question Answering","url":"/task/conversational-question-answering","datasets_with_task":"/datasets/task/conversational-question-answering"},{"name":"Conversational Response Generation","url":"/task/conversational-response-generation","datasets_with_task":"/datasets/task/conversational-response-generation"},{"name":"AI Agent","url":"/task/ai-agent","datasets_with_task":"/datasets/task/ai-agent"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["diaforge-utc-r-0725"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}