# Chitchat as Interference: Adding User Backstories to Task-Oriented Dialogues

arXiv: https://arxiv.org/abs/2402.15248 · HTML: https://mlsanity.com/paper/2402.15248/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 23 Feb 2024.

## Builds on (most cited first, 21 of 21)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [A Survey on Dialogue Systems: Recent Advances and New Frontiers](https://mlsanity.com/paper/1711.01731/) (2017)
- [Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills](https://mlsanity.com/paper/2004.08449/) (2020)
- [Survey on Evaluation Methods for Dialogue Systems](https://mlsanity.com/paper/1905.04071/) (2019)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [Best-Worst Scaling More Reliable than Rating Scales: A Case Study on Sentiment Intensity Annotation](https://mlsanity.com/paper/1712.01765/) (2017)
- [SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents](https://mlsanity.com/paper/2305.13040/) (2023)
- [Are LLMs All You Need for Task-Oriented Dialogue?](https://mlsanity.com/paper/2304.06556/) (2023)
- [Adding Chit-Chat to Enhance Task-Oriented Dialogues](https://mlsanity.com/paper/2010.12757/) (2020)
- [Shades of BLEU, Flavours of Success: The Case of MultiWOZ](https://mlsanity.com/paper/2106.05555/) (2021)
- [Controllable Dialogue Simulation with In-Context Learning](https://mlsanity.com/paper/2210.04185/) (2022)
- [Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions](https://mlsanity.com/paper/2006.12442/) (2020)
- [Fusing task-oriented and open-domain dialogues in conversational agents](https://mlsanity.com/paper/2109.04137/) (2021)
- [AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2209.03632/) (2022)
- [Enhancing Task Bot Engagement with Synthesized Open-Domain Dialog](https://mlsanity.com/paper/2212.10008/) (2022)
- [System-Initiated Transitions from Chit-Chat to Task-Oriented Dialogues with Transition Info Extractor and Transition Sentence Generator](https://mlsanity.com/paper/2308.03098/) (2023)
- [Enhancing Task-Oriented Dialogues with Chitchat: a Comparative Study Based on Lexical Diversity and Divergence](https://mlsanity.com/paper/2311.14067/) (2023)

## Built on by (most cited first, 4 of 4)

- [PicPersona-TOD : A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona](https://mlsanity.com/paper/2504.17390/) (2025)
- [Beyond Task-Oriented and Chitchat Dialogues: Proactive and Transition-Aware Conversational Agents](https://mlsanity.com/paper/2511.08835/) (2025)
- [Disambiguation of Emotion Annotations by Contextualizing Events in Plausible Narratives](https://mlsanity.com/paper/2508.09954/) (2025)
- [DiagFlowBench: Evaluating How Language Models Handle Off-Procedure Inputs in Grounded Diagnostic Dialogue](https://mlsanity.com/paper/2606.17904/) (2026)

## Abstract (arXiv)

During task-oriented dialogues (TODs), human users naturally introduce chitchat that is beyond the immediate scope of the task, interfering with the flow of the conversation. To address this issue without the need for expensive manual data creation, we use few-shot prompting with Llama-2-70B to enhance the MultiWOZ dataset with user backstories, a typical example of chitchat interference in TODs. We assess the impact of this addition by testing two models: one trained solely on TODs and another trained on TODs with a preliminary chitchat interaction. Our analysis demonstrates that our enhanced dataset poses a challenge for these systems. Moreover, we demonstrate that our dataset can be effectively used for training purposes, enabling a system to consistently acknowledge the user's backstory while also successfully moving the task forward in the same turn, as confirmed by human evaluation. These findings highlight the benefits of generating novel chitchat-TOD scenarios to test TOD systems more thoroughly and improve their resilience to natural user interferences