RASTeR: Robust, Agentic, and Structured Temporal Reasoning
Dan Schumacher, Fatemeh Haji, Tara Grey, Niharika Bandlamudi, Nupoor Karnik, Gagana Uday Kumar, Jason Cho-Yu Chiang, Paul Rad, Nishant Vishwamitra, Anthony Rios

TL;DR
RASTeR is a prompting framework that enhances large language models' ability to perform reliable temporal question answering by evaluating context relevance, constructing temporal knowledge graphs, and correcting inconsistencies, especially under noisy or outdated information.
Contribution
The paper introduces RASTeR, a novel prompting framework that separates context evaluation from answer generation, improving robustness in temporal reasoning tasks for LLMs.
Findings
RASTeR improves accuracy by over 12% compared to baselines.
It maintains 75% accuracy with 40 distractors in noisy contexts.
RASTeR outperforms existing methods across multiple datasets and models.
Abstract
Temporal question answering (TQA) remains a challenge for large language models (LLMs), particularly when retrieved content may be irrelevant, outdated, or temporally inconsistent. This is especially critical in applications like clinical event ordering, and policy tracking, which require reliable temporal reasoning even under noisy or outdated information. To address this challenge, we introduce RASTeR: \textbf{R}obust, \textbf{A}gentic, and \textbf{S}tructured, \textbf{Te}mporal \textbf{R}easoning, a prompting framework that separates context evaluation from answer generation. RASTeR first assesses the relevance and temporal coherence of the retrieved context, then constructs a temporal knolwedge graph (TKG) to better facilitate reasoning. When inconsistencies are detected, RASTeR selectively corrects or discards context before generating an answer. Across multiple datasets and LLMs,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTopic Modeling · Speech and dialogue systems · Natural Language Processing Techniques
