Factors affecting the in-context learning abilities of LLMs for dialogue state tracking

Pradyoth Hegde, Santosh Kesiraju, Jan Švec, Šimon Sedláček, Bolaji Yusuf +3 more
6/10/2025
cs.CLcs.AI

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

This study explores the application of in-context learning (ICL) to the dialogue state tracking (DST) problem and investigates the factors that influence its effectiveness. We use a sentence embedding based k-nearest neighbour method to retrieve the suitable demonstrations for ICL. The selected demonstrations, along with the test samples, are structured within a template as input to the LLM. We then conduct a systematic study to analyse the impact of factors related to demonstration selection and prompt context on DST performance. This work is conducted using the MultiWoZ2.4 dataset and focuses primarily on the OLMo-7B-instruct, Mistral-7B-Instruct-v0.3, and Llama3.2-3B-Instruct models. Our findings provide several useful insights on in-context learning abilities of LLMs for dialogue state tracking.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Improving Dialogue State Tracking through Combinatorial Search for In-Context Examples

84% match2025

Intent-driven In-context Learning for Few-shot Dialogue State Tracking

83% match2024

Misconfidence-based Demonstration Selection for LLM In-Context Learning

83% match2024

Is In-Context Learning Sufficient for Instruction Following in LLMs?

83% match1 repo342026

Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation

83% match2024

The Speech-LLM Takes It All: A Truly Fully End-to-End Spoken Dialogue State Tracking Approach

82% match2025

Cite this paper

@article{hegde2025factors,
  title  = {Factors affecting the in-context learning abilities of LLMs for dialogue state tracking},
  author = {Pradyoth Hegde and Santosh Kesiraju and Jan Švec and Šimon Sedláček and Bolaji Yusuf and Oldřich Plchot and Deepak K T and Jan Černocký},
  year   = {2025},
  eprint = {2506.08753},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2506.08753v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2506.08753.svg)](https://codeofpaper.com/paper/2506.08753)

Discussion