mlsanityData to 14 Oct 2026

Multi-trait User Simulation with Adaptive Decoding for Conversational Task Assistants

arXiv 2410.12891 ↗First posted 16 Oct 2024cs.CL cs.AI cs.HCcited by 5

Not on the map. Why?

Abstract (arXiv)

Conversational systems must be robust to user interactions that naturally exhibit diverse conversational traits. Capturing and simulating these diverse traits coherently and efficiently presents a complex challenge. This paper introduces Multi-Trait Adaptive Decoding (mTAD), a method that generates diverse user profiles at decoding-time by sampling from various trait-specific Language Models (LMs). mTAD provides an adaptive and scalable approach to user simulation, enabling the creation of multiple user profiles without the need for additional fine-tuning. By analyzing real-world dialogues from the Conversational Task Assistant (CTA) domain, we identify key conversational traits and developed a framework to generate profile-aware dialogues that enhance conversational diversity. Experimental results validate the effectiveness of our approach in modeling single-traits using specialized LMs, which can capture less common patterns, even in out-of-domain tasks. Furthermore, the results demonstrate that mTAD is a robust and flexible framework for combining diverse user simulators.

Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 28 of its 46 references that are in the map. First posted on arXiv 16 Oct 2024.

Builds on

28 of 46 references.

References · 28

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  4. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  5. 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,418
  6. 2019HuggingFace's Transformers: State-of-the-art Natural Language Processingcited by 2,218
  7. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,396
  8. 2023TIES-Merging: Resolving Interference When Merging Modelscited by 818
  9. 2018MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modellingcited by 766
  10. 2023Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunchcited by 694
  11. 2023An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuningcited by 639
  12. 2019Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Datasetcited by 434
16 more
  1. 2018Towards Deep Conversational Recommendationscited by 176
  2. 2024LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMscited by 84
  3. 2020Interactive Path Reasoning on Graph for Conversational Recommendationcited by 72
  4. 2022TweetNLP: Cutting-Edge Natural Language Processing for Social Mediacited by 71
  5. 2024Learning to Decode Collaboratively with Multiple Language Modelscited by 62
  6. 2016A User Simulator for Task-Completion Dialoguescited by 57
  7. 2020Evaluating Conversational Recommender Systems via User Simulationcited by 47
  8. 2019How to Build User Simulators to Train RL-based Dialog Systemscited by 46
  9. 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
  10. 2023KuaiSim: A Comprehensive Simulator for Recommender Systemscited by 30
  11. 2021Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systemscited by 23
  12. 2022Alexa, Let's Work Together: Introducing the First Alexa Prize TaskBot Challenge on Conversational Task Assistancecited by 15
  13. 2022Classifiers are Better Experts for Controllable Text Generationcited by 11
  14. 2023UserSimCRS: A User Simulation Toolkit for Evaluating Conversational Recommender Systemscited by 11
  15. 2024Plan-Grounded Large Language Models for Dual Goal Conversational Settingscited by 8
  16. 2023"Mango Mango, How to Let The Lettuce Dry Without A Spinner?": Exploring User Perceptions of Using An LLM-Based Conversational Assistant Toward Cooking Partnercited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 3.

5 papers.

  1. 2025Flipping the Dialogue: Training and Evaluating User Language Modelscited by 58
  2. 2025Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profilescited by 41
  3. 2026WRIT: Write-Read Intensive Trajectory Synthesis for Multi-Turn User-Facing Agentscited by 2
  4. 2026"Act Like a 5th Grader" is Not Enough: Bounding Knowledge in LLM-Based User Simulatorscited by 0
  5. 2026Large-Scale User Behavior Analysis in Multimodal AI-Assisted Manual Task Executioncited by 0