The paper introduces a covariance‑corrected Mahalanobis distance method for detecting out‑of‑domain (OOD) intents in conversational agents. It builds on prior work showing Mahalanobis distance’s effectiveness but addresses its shortcomings in few‑shot scenarios, where limited examples of new intents are available. The authors analyze why the original approach underperforms and propose a refined distance metric to improve OOD detection in practical settings.
By Jayasimha Talur, Oleg Smirnov, Paul Missault
The paper evaluates whether zero‑shot large language models (LLMs) can replace fine‑tuned natural language understanding (NLU) classifiers for intent detection in conversational systems. Experiments on ATIS and CLINC150 show that fine‑tuned RoBERTa outperforms Claude Haiku zero‑shot when ample in‑domain labels are available, but the LLM matches the supervised model on the broader 150‑intent CLINC150 schema. The authors identify three production‑relevant scenarios where LLMs excel—out‑of‑scope detection, robustness to ASR noise, and dynamic per‑deployment schemas—and present a decision framework to guide practitioners.
whyItMatters:"The study provides concrete evidence and a practical framework for deciding when to deploy LLMs versus fine‑tuned models in real‑world conversational applications."
By Carson Rodrigues, Oysturn Vas
arXiv:2607. 27421v1 Announce Type: cross Abstract: Intent classification is a core component of task-oriented dialogue systems, yet practitioners have limited systematic guidance for selecting deployable open-weight language models under compute, latency, and robustness constraints.
By Parishruthi Ganesh, Gerry Dozier, Cheryl Seals
arXiv:2511. 08378v4 Announce Type: replace-cross Abstract: Session-based recommendation (SBR) aims to predict anonymous users' next interaction based on their interaction sessions.
By Xiao Wang, Ke Qin, Dongyang Zhang, Xiurui Xie, Shuang Liang
arXiv:2511. 05913v2 Announce Type: replace-cross Abstract: New intent discovery (NID) seeks to recognize both new and known intents from unlabeled user utterances, which finds prevalent use in practical dialogue systems.
By Hongtao Wang, Renchi Yang, Wenqing Lin
IntentCoding is a decoding strategy that amplifies user intent in large language model code generation by masking the intent and applying a multi‑strength ensemble mechanism. It is model‑agnostic, requires no extra training, and integrates with existing decoding procedures. Experiments on the new CodeConstraints benchmark and other datasets show significant improvements in constraint satisfaction and functional correctness, with up to 71.0% relative gains on CodeConstraints and 29.3% on HumanEval and LiveCodeBench compared to greedy decoding.
By Zheng Fang, Yihong Dong, Lili Mou, Dongming Jin, Zhi Jin, Ge Li
arXiv:2608. 10939v1 Announce Type: cross Abstract: Multilingual short-text classification supports operational systems such as content moderation, customer support routing, and intent recognition, yet aggregate evaluation often hides large differences between high-resource and low-resource languages.
By Wajdi Ben Saad, Safa Madiouni
arXiv:2405. 12775v2 Announce Type: replace-cross Abstract: Discovering the semantics of multimodal utterances is essential for understanding human language and enhancing human-machine interactions.
By Hanlei Zhang, Hua Xu, Fei Long, Xin Wang, Kai Gao
MISApp is a profile‑free framework that predicts the next mobile app a user will launch by learning multi‑hop session graphs. It captures transition dependencies across different structural ranges, incorporates temporal context and spatial categorization, and models intent evolution from recent interactions. Experiments on two real‑world datasets show MISApp outperforms baselines in both standard and cold‑start settings while remaining efficient, and analyses reveal that multi‑hop relations provide higher‑order predictive signals and interpretable attention weights.
By Yunchi Yang, Longlong Li, Jianliang Wu, Cunquan Qu
arXiv:2609.36115v1 Announce Type: new
Abstract: Industry applications often demand low-latency classification, yet current large language model (LLM) approaches remain poorly suited for latency-criti...
By Shenghong Dai, Shiva Kumar Pentyala, Yingchi Liu, Shubham Mehrotra, Suman Banerjee, James Zhu, Bin Bi, Sitaram Asur, Phil Mui
DeepOpen is a decision‑oriented intent‑classification framework tailored for the BANKING77 and CLINC150 datasets. On BANKING77, a single English classifier trained with sharpness‑aware minimization (SAM) achieved a test accuracy of 94.1234% (2,899/3,080), the highest among three fixed SAM seeds. For CLINC150, a probability fusion of one Laya specialist and three DeBERTa‑v3‑large classifiers reached 98.0222% accuracy (4,411/4,500). The study reports strong task‑specific performance, notes selection effects, and highlights unresolved historical execution‑path differences rather than a new algorithmic advantage.
By Shuang Song, Muhammad Luqman Naseem, Zhongqiao Yuan
The paper introduces an uncertainty‑aware probabilistic framework for continual discovery of new user intents in open‑world settings where the label space evolves. It encodes utterances with an adaptive β‑VAE, uses classifier confidence, posterior uncertainty, and DP‑GMM likelihood to separate known from novel intents, and promotes only reliable clusters to new labels while employing replay and Elastic Weight Consolidation to avoid forgetting. Experiments demonstrate high novelty precision, stable adaptation across phases, and limited forgetting, with qualitative results showing coherent semantic clusters despite conservative label expansion.
By Pisante Aida, Formentin Simone