# Reasoning over Object Descriptions Improves Coreference Resolution in Task-Based Dialogue Systems

arXiv: https://arxiv.org/abs/2604.27850 · HTML: https://mlsanity.com/paper/2604.27850/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 17 of its 44 references that are in the map.
- First posted on arXiv 30 Apr 2026.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 17 of 17)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [Gemma: Open Models Based on Gemini Research and Technology](https://mlsanity.com/paper/2403.08295/) (2024)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [A Survey of Context Engineering for Large Language Models](https://mlsanity.com/paper/2507.13334/) (2025)
- [The Surprising Effectiveness of Test-Time Training for Few-Shot Learning](https://mlsanity.com/paper/2411.07279/) (2024)
- [SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations](https://mlsanity.com/paper/2104.08667/) (2021)
- [The JDDC Corpus: A Large-Scale Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service](https://mlsanity.com/paper/1911.09969/) (2019)
- [Situated and Interactive Multimodal Conversations](https://mlsanity.com/paper/2006.01460/) (2020)
- [The JDDC 2.0 Corpus: A Large-Scale Multimodal Multi-Turn Chinese Dialogue Dataset for E-commerce Customer Service](https://mlsanity.com/paper/2109.12913/) (2021)
- [MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines](https://mlsanity.com/paper/1907.01669/) (2019)
- [UNITER-Based Situated Coreference Resolution with Rich Multimodal Input](https://mlsanity.com/paper/2112.03521/) (2021)

## Abstract (arXiv)

Task-based dialogue systems assist users in achieving specific goals, such as executing actions or retrieving information, through natural language interactions. Accurate coreference resolution is essential, as it involves identifying object references within the dialogue - a task that becomes increasingly challenging in visually grounded environments characterized by complex scenes and diverse object metadata. However, coreference resolution in task-based dialogue remains limited by poor generalization across domains and heavy reliance on supervised models that often overfit to dataset-specific artifacts. In this work, we propose a unimodal test-time reasoning approach that enables large language models (LLMs) to reason over detailed object metadata and dialogue history to improve coreference resolution. Empirical results on the SIMMC 2.1 dataset demonstrate that LLMs can generate step-by-step reasoning processes that effectively align dialogue context with objects present in the scene. Extensive experiments highlight the models' ability to link conversations and objects accurately. Moreover, we show that test-time reasoning under few-shot settings generalizes effectively to unseen scenarios and novel objects, outperforming encoder-based supervised methods in cross-domain evaluations. These findings underscore the critical role of structured metadata and careful prompt engineering in enhancing the robustness and generalization of task-oriented dialogue systems.