# Evaluating Temporal Consistency in Multi-Turn Language Models

arXiv: https://arxiv.org/abs/2604.23051 · HTML: https://mlsanity.com/paper/2604.23051/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 24 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [CoQA: A Conversational Question Answering Challenge](https://mlsanity.com/paper/1808.07042/) (2018)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback](https://mlsanity.com/paper/2309.10691/) (2023)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension](https://mlsanity.com/paper/1902.00164/) (2019)
- [A Dataset for Answering Time-Sensitive Questions](https://mlsanity.com/paper/2108.06314/) (2021)
- [Entity-Relation Extraction as Multi-Turn Question Answering](https://mlsanity.com/paper/1905.05529/) (2019)
- [Improving Multi-turn Dialogue Modelling with Utterance ReWriter](https://mlsanity.com/paper/1906.07004/) (2019)
- [Learning without training: The implicit dynamics of in-context learning](https://mlsanity.com/paper/2507.16003/) (2025)
- [MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming](https://mlsanity.com/paper/2505.17147/) (2025)
- [ArchivalQA: A Large-scale Benchmark Dataset for Open Domain Question Answering over Historical News Collections](https://mlsanity.com/paper/2109.03438/) (2021)
- [Is Your LLM Outdated? A Deep Look at Temporal Generalization](https://mlsanity.com/paper/2405.08460/) (2024)
- [Time-R1: Towards Comprehensive Temporal Reasoning in LLMs](https://mlsanity.com/paper/2505.13508/) (2025)
- [Firm or Fickle? Evaluating Large Language Models Consistency in Sequential Interactions](https://mlsanity.com/paper/2503.22353/) (2025)
- [No Need for Explanations: LLMs can implicitly learn from mistakes in-context](https://mlsanity.com/paper/2502.08550/) (2025)
- [Understanding Knowledge Drift in LLMs through Misinformation](https://mlsanity.com/paper/2409.07085/) (2024)
- [WILT: A Multi-Turn, Memorization-Robust Inductive Logic Benchmark for LLMs](https://mlsanity.com/paper/2410.10998/) (2024)
- [TCP: a Benchmark for Temporal Constraint-Based Planning](https://mlsanity.com/paper/2505.19927/) (2025)
- [Empirical Characterization of Temporal Constraint Processing in LLMs](https://mlsanity.com/paper/2511.10654/) (2025)

## Built on by (most cited first, 1 of 1)

- [MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation](https://mlsanity.com/paper/2605.27186/) (2026)

## Abstract (arXiv)

Language models are increasingly deployed in interactive settings where users reason about facts over time rather than in isolation. In such scenarios, correct behavior requires models to maintain and update implicit temporal assumptions established earlier in a conversation. We study this challenge through the lens of temporal scope stability: the ability to preserve, override, or transfer time-scoped factual context across dialogue turns. We introduce ChronoScope, a large-scale diagnostic benchmark designed to isolate temporal scope behavior in controlled multi-turn interactions, comprising over one million deterministically generated question chains grounded in Wikidata. ChronoScope evaluates whether models can correctly retain inferred temporal scope when follow-up questions omit explicit time references, spanning implicit carryover, explicit scope switching, cross-entity transfer, and longer temporal trajectories. Through extensive evaluation of state-of-the-art language models, we find that temporal scope stability is frequently violated in controlled multi-turn settings, with models often drifting toward present-day assumptions despite correct underlying knowledge. These failures intensify with interaction length and persist even under oracle context conditions, revealing a gap between single-turn factual accuracy and coherent temporal reasoning under sequential interaction. We make our dataset and evaluation suite publicly available at https://github.com/yashkumaratri/ChronoScope