Saved in:
Bibliographic Details
Main Authors: Sinha, Aditya, Steck, Harald, Ostuni, Vito, Rinaldi, Matteo
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.09268
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914548761493504
author Sinha, Aditya
Steck, Harald
Ostuni, Vito
Rinaldi, Matteo
author_facet Sinha, Aditya
Steck, Harald
Ostuni, Vito
Rinaldi, Matteo
contents Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns, leading to inaccurate responses. In this paper, we stress-test the multi-turn understanding of LLMs and study the following two sub-tasks: (1) detecting whether the user pivots or refines in the current turn, and (2) shortlisting relevant context from previous turns. To this end, we construct synthetic benchmarks based on real-world datasets from varied domains, as to simulate context shifts of different levels of difficulty. We then evaluate the zero-shot performance of ten LLMs (open-weight, closed-source and reasoning), and demonstrate that only some reasoning and strongly instructed LLMs are accurate in detecting pivots; open-weight LLMs struggle with the task and frequently carry stale context even with explicit cues; and all models suffer from a position bias. Based on the results, we discuss key takeaways for improving long-term robustness in multi-turn capabilities for LLMs.
format Preprint
id arxiv_https___arxiv_org_abs_2605_09268
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
Sinha, Aditya
Steck, Harald
Ostuni, Vito
Rinaldi, Matteo
Computation and Language
Artificial Intelligence
Users interacting with Large Language Models (LLMs) in a multi-turn conversation routinely refine their requests or pivot to new topics. LLMs, however, often miss these topic shifts and carry over irrelevant context from previous turns, leading to inaccurate responses. In this paper, we stress-test the multi-turn understanding of LLMs and study the following two sub-tasks: (1) detecting whether the user pivots or refines in the current turn, and (2) shortlisting relevant context from previous turns. To this end, we construct synthetic benchmarks based on real-world datasets from varied domains, as to simulate context shifts of different levels of difficulty. We then evaluate the zero-shot performance of ten LLMs (open-weight, closed-source and reasoning), and demonstrate that only some reasoning and strongly instructed LLMs are accurate in detecting pivots; open-weight LLMs struggle with the task and frequently carry stale context even with explicit cues; and all models suffer from a position bias. Based on the results, we discuss key takeaways for improving long-term robustness in multi-turn capabilities for LLMs.
title Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2605.09268