End-to-end Task-Oriented Dialog (TOD) systems typically require extensive training datasets to perform well.In contrast, large language model (LLM) based TOD systems can excel even with limited data due to their ability to learn tasks through in-context exemplars.However, these models lack alignment with the style of responses in training data and often generate comprehensive responses, making it difficult for users to grasp the information quickly.In response, we propose SyncTOD that synergizes LLMs with task-specific hints to improve alignment in low-data settings.Sync-TOD employs small auxiliary models to provide hints and select exemplars for in-context prompts.With ChatGPT, SyncTOD achieves superior performance compared to LLM-based baselines and SoTA models in low-data settings, while retaining competitive performance in full-data settings.

Medical task-oriented dialogue systems can assist doctors by collecting patient medical history, aiding in diagnosis, or guiding treatment selection, thereby reducing doctor burnout and expanding access to medical services.However, doctor-patient dialogue datasets are not readily available, primarily due to privacy regulations.Moreover, existing datasets lack comprehensive annotations involving medical slots and their different attributes, such as symptoms and their onset, progression, and severity.These comprehensive annotations are crucial for accurate diagnosis.Finally, most existing datasets are non-English, limiting their utility for the larger research community.In response, we introduce MediTOD, a new dataset of doctor-patient dialogues in English for the medical history-taking task.Collaborating with doctors, we devise a questionnairebased labeling scheme tailored to the medical domain.Then, medical professionals create the dataset with high-quality comprehensive annotations, capturing medical slots and their attributes.We establish benchmarks in supervised and few-shot settings on MediTOD for natural language understanding, policy learning, and natural language generation subtasks, evaluating models from both TOD and biomedical domains.We release MediTOD resources for future research.* Work done when authors were at IIT Delhi.[{"intent": "salutations"}] Doctor: How may I help you?[{"intent": "inform", "slots": { "positive_symptom": [ {"value": "pharyngitis", "onset": "past four days"}, {"value": "fever", "onset": "last two days"} ]}}] Patient: Yes, I just came in here today.I I've just been.Really getting like the soreness in my throat for the past, I would say four days and I also had a fever for the last two days as well. CMAS Key-Value Legends:[{"intent": "inform", "slots": { "positive_symptom": "pharyngitis", "positive_symptom": "fever", "onset": "past four days", "onset": "last two days" }] Datasets Language Annotations #utterances/ #utterancesAll TOD Tasks Comprehensive Canonicalized dialogue