Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912460522389504 |
|---|---|
| author | Zaera, Álvaro Popa, Diana Nicoleta Sekulic, Ivan Rosso, Paolo |
| author_facet | Zaera, Álvaro Popa, Diana Nicoleta Sekulic, Ivan Rosso, Paolo |
| contents | Out-of-scope (OOS) intent detection is a critical challenge in task-oriented dialogue systems (TODS), as it ensures robustness to unseen and ambiguous queries. In this work, we propose a novel but simple modular framework that combines uncertainty modeling with fine-tuned large language models (LLMs) for efficient and accurate OOS detection. The first step applies uncertainty estimation to the output of an in-scope intent detection classifier, which is currently deployed in a real-world TODS handling tens of thousands of user interactions daily. The second step then leverages an emerging LLM-based approach, where a fine-tuned LLM is triggered to make a final decision on instances with high uncertainty. Unlike prior approaches, our method effectively balances computational efficiency and performance, combining traditional approaches with LLMs and yielding state-of-the-art results on key OOS detection benchmarks, including real-world OOS data acquired from a deployed TODS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_01541 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing Zaera, Álvaro Popa, Diana Nicoleta Sekulic, Ivan Rosso, Paolo Computation and Language Out-of-scope (OOS) intent detection is a critical challenge in task-oriented dialogue systems (TODS), as it ensures robustness to unseen and ambiguous queries. In this work, we propose a novel but simple modular framework that combines uncertainty modeling with fine-tuned large language models (LLMs) for efficient and accurate OOS detection. The first step applies uncertainty estimation to the output of an in-scope intent detection classifier, which is currently deployed in a real-world TODS handling tens of thousands of user interactions daily. The second step then leverages an emerging LLM-based approach, where a fine-tuned LLM is triggered to make a final decision on instances with high uncertainty. Unlike prior approaches, our method effectively balances computational efficiency and performance, combining traditional approaches with LLMs and yielding state-of-the-art results on key OOS detection benchmarks, including real-world OOS data acquired from a deployed TODS. |
| title | Efficient Out-of-Scope Detection in Dialogue Systems via Uncertainty-Driven LLM Routing |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.01541 |