Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky

[2507.03336] Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Artificial Intelligence arXiv:2507.03336 (cs) [Submitted on 4 Jul 2025 ( v1 ), last revised 11 Apr 2026 (this version, v4)] Title: Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky Authors: Ashutosh Hathidara , Julien Yu , Sebastian Schreiber View a PDF of the paper titled Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky, by Ashutosh Hathidara and 2 other authors View PDF HTML (experimental) Abstract: Large language models (LLMs) are increasingly tasked with invoking enterprise APIs, yet they routinely falter when near-duplicate tools vie for the same user intent or when required arguments are left underspecified. We introduce DiaFORGE (Dialogue Framework for Organic Response Generation & Evaluation), a disambiguation-centric, three-stage pipeline that (i) synthesizes persona-driven, multi-turn dialogues in which the assistant must distinguish among highly similar tools, (ii) performs supervised fine-tuning of open-source models with reasoning traces across 3B - 70B parameters, and (iii) evaluates real-world readiness via a dynamic suite that redeploys each model in a live agentic loop and reports end-to-end goal completion alongside conventional static metrics. On our dynamic benchmark DiaBENCH, models trained with DiaFORGE raise tool-invocation success by 27 pp over GPT-4o and by 49 pp over Claude-3.5-Sonnet, both under optimized prompting. To spur further research, we release an open corpus of 5000 production-grade enterprise API specifications paired with rigorously validated, disambiguation-focused dialogues, offering a practical blueprint for building reliable, enterprise-ready tool-calling agents. Comments: ACL 2026 Findings Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Machine Learning (cs.LG) Cite as: arXiv:2507.03336 [cs.AI] (or arXiv:2507.03336v4 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2507.03336 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ashutosh Hathidara [ view email ] [v1] Fri, 4 Jul 2025 06:49:02 UTC (9,670 KB) [v2] Mon, 4 Aug 2025 15:48:55 UTC (9,670 KB) [v3] Thu, 9 Oct 2025 16:01:00 UTC (9,889 KB) [v4] Sat, 11 Apr 2026 23:29:44 UTC (603 KB) Full-text links: Access Paper: View a PDF of the paper titled Disambiguation-Centric Finetuning Makes Enterprise Tool-Calling LLMs More Realistic and Less Risky, by Ashutosh Hathidara and 2 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.AI < prev | next > new | recent | 2025-07 Change to browse by: cs cs.CL cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Corporate Language Model (CLM): Transforming Tacit and Fragmented Enterprise Knowledge into a Sovereign, Auditable, and Executable Corporate Intelligence Layer#927671
• Exploring Individual Factors in the Adoption of LLMs for Specific Software Engineering Purposes#141723
• "If You're Not Doing It, Somebody Else Is": Active Negotiation and the Invisible Labor of Sustained LLM Use#1105258
• In-Place Tokenizer Expansion for Pre-trained LLMs#373372
• Visible but Not Yet Curatable: Characterizing the Curatability of Compact and Derived Open LLM Artifacts#793057