Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs

• URL: http://arxiv.org/abs/2605.09268v1
• Date: Sun, 10 May 2026 02:28:23 GMT
• Title: Beyond Continuity: Challenges of Context Switching in Multi-Turn Dialogue with LLMs
• Abstract summary: We stress-test the multi-turn understanding of Large Language Models (LLMs)<n>We study the following two sub-tasks: detecting whether the user pivots or refines in the current turn, and shortlisting relevant context from previous turns.<n>We evaluate the zero-shot performance of ten LLMs (open-weight, closed-source and reasoning)
• Score: 6.89598705331814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Intent Mismatch Causes LLMs to Get Lost in Multi-Turn Conversation [26.91734024759386]
  We argue that the root cause lies in an intent alignment gap rather than intrinsic capability deficits.<n>We propose to decouple intent understanding from task execution through a Mediator-Assistant architecture.
  arXiv  Detail & Related papers  (2026-02-07T03:41:04Z)
• LLMs Get Lost In Multi-Turn Conversation [44.26588510453331]
  Large Language Models (LLMs) are conversational interfaces.<n>LLMs have the potential to assist their users not only when they can fully specify the task at hand, but also to help them define, explore, and refine what they need through multi-turn conversational exchange.
  arXiv  Detail & Related papers  (2025-05-09T15:21:44Z)
• Position: Empowering Time Series Reasoning with Multimodal LLMs [49.73647759532127]
  We argue that multimodal language models (MLLMs) can enable more powerful and flexible reasoning for time series analysis.<n>We call on researchers and practitioners to leverage this potential by developing strategies that prioritize trust, interpretability, and robust reasoning in MLLMs.
  arXiv  Detail & Related papers  (2025-02-03T16:10:48Z)
• FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs [8.37667737406383]
  We propose a fairness benchmark for large language model (LLM)-based chatbots in multi-turn dialogue scenarios, textbfFairMT-Bench.<n>To ensure coverage of diverse bias types and attributes, we employ our template to construct a multi-turn dialogue dataset, textttFairMT-10K.<n>Experiments and analyses on textttFairMT-10K reveal that in multi-turn dialogue scenarios, current LLMs are more likely to generate biased responses, and there is significant variation in performance across different tasks and models.
  arXiv  Detail & Related papers  (2024-10-25T06:06:31Z)
• Beyond the Turn-Based Game: Enabling Real-Time Conversations with Duplex Models [66.24055500785657]
  Traditional turn-based chat systems prevent users from verbally interacting with system while it is generating responses. To overcome these limitations, we adapt existing LLMs to listen users while generating output and provide users with instant feedback. We build a dataset consisting of alternating time slices of queries and responses as well as covering typical feedback types in instantaneous interactions.
  arXiv  Detail & Related papers  (2024-06-22T03:20:10Z)
• MathChat: Benchmarking Mathematical Reasoning and Instruction Following in Multi-Turn Interactions [58.57255822646756]
  This paper introduces MathChat, a benchmark designed to evaluate large language models (LLMs) across a broader spectrum of mathematical tasks. We evaluate the performance of various SOTA LLMs on the MathChat benchmark, and we observe that while these models excel in single turn question answering, they significantly underperform in more complex scenarios. We develop MathChat sync, a synthetic dialogue based math dataset for LLM finetuning, focusing on improving models' interaction and instruction following capabilities in conversations.
  arXiv  Detail & Related papers  (2024-05-29T18:45:55Z)
• Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding [78.36702055076456]
  This paper introduces Multi-scale Positional. (Ms-PoE) which is a simple yet effective plug-and-play approach to enhance the capacity of. LLMs to handle relevant information located in the middle of the context.
  arXiv  Detail & Related papers  (2024-03-05T04:58:37Z)
• Benchmarking LLMs on the Semantic Overlap Summarization Task [7.944123371140184]
  We perform a benchmarking study of popular Large Language Models (LLMs) exclusively on the Semantic Overlap Summarization (SOS) task.<n>This dataset provides 135 high-quality SOS data samples sourced from privacy policy documents.<n>We then use a standard prompting taxonomy called TELeR to create and evaluate 905,216 distinct LLM-generated summaries over two SOS datasets.
  arXiv  Detail & Related papers  (2024-02-26T20:33:50Z)
• Rethinking Interpretability in the Era of Large Language Models [76.1947554386879]
  Large language models (LLMs) have demonstrated remarkable capabilities across a wide array of tasks. The capability to explain in natural language allows LLMs to expand the scale and complexity of patterns that can be given to a human. These new capabilities raise new challenges, such as hallucinated explanations and immense computational costs.
  arXiv  Detail & Related papers  (2024-01-30T17:38:54Z)
• Blinded by Generated Contexts: How Language Models Merge Generated and Retrieved Contexts When Knowledge Conflicts? [45.233517779029334]
  We identify whether responses are attributed to generated or retrieved contexts. Experiments reveal a significant bias in several LLMs to favor generated contexts, even when they provide incorrect information.
  arXiv  Detail & Related papers  (2024-01-22T12:54:04Z)
• TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models [52.734140807634624]
  Aligned large language models (LLMs) demonstrate exceptional capabilities in task-solving, following instructions, and ensuring safety. Existing continual learning benchmarks lack sufficient challenge for leading aligned LLMs. We introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
  arXiv  Detail & Related papers  (2023-10-10T16:38:49Z)
• MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback [78.60644407028022]
  We introduce MINT, a benchmark that evaluates large language models' ability to solve tasks with multi-turn interactions. LLMs generally benefit from tools and language feedback, with performance gains of 1-8% for each turn of tool use. LLMs evaluated, supervised instruction-finetuning (SIFT) and reinforcement learning from human feedback (RLHF) generally hurt multi-turn capabilities.
  arXiv  Detail & Related papers  (2023-09-19T15:25:42Z)
• Investigating Answerability of LLMs for Long-Form Question Answering [35.41413072729483]
  We focus on long-form question answering (LFQA) because it has several practical and impactful applications. We propose a question-generation method from abstractive summaries and show that generating follow-up questions from summaries of long documents can create a challenging setting.
  arXiv  Detail & Related papers  (2023-09-15T07:22:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.