No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning

• URL: http://arxiv.org/abs/2506.11246v1
• Date: Thu, 12 Jun 2025 19:32:59 GMT
• Title: No Universal Prompt: Unifying Reasoning through Adaptive Prompting for Temporal Table Reasoning
• Abstract summary: Temporal Table Reasoning is a critical challenge for Large Language Models (LLMs)<n>Despite existence of multiple prompting methods, their impact on table reasoning remains largely unexplored.<n>This work investigates multiple prompting technique across diverse table types to determine optimal approaches for different scenarios.
• Score: 44.50201310715929
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Temporal Table Reasoning is a critical challenge for Large Language Models (LLMs), requiring effective prompting techniques to extract relevant insights. Despite existence of multiple prompting methods, their impact on table reasoning remains largely unexplored. Furthermore, the performance of these models varies drastically across different table and context structures, making it difficult to determine an optimal approach. This work investigates multiple prompting technique across diverse table types to determine optimal approaches for different scenarios. We find that performance varies based on entity type, table structure, requirement of additional context and question complexity, with NO single method consistently outperforming others. To mitigate these challenges, we introduce SEAR, an adaptive prompting framework inspired by human reasoning that dynamically adjusts based on context characteristics and integrates a structured reasoning. Our results demonstrate that SEAR achieves superior performance across all table types compared to other baseline prompting techniques. Additionally, we explore the impact of table structure refactoring, finding that a unified representation enhances model's reasoning.

Related papers

• PARTAB: Partition-Aware Reasoning with Structured Evidence for Scalable Table Understanding [10.971852280240357]
  Partition-Aware Reasoning overTables (Partition-Aware Reasoning overTables)<n>Partition-Aware Reasoning overTables (Partition-Aware Reasoning overTables)<n>Partition-Aware Reasoning overTables (Partition-Aware Reasoning overTables)
  arXiv  Detail & Related papers  (2026-08-25T05:26:23Z)
• TABVERSE: Benchmarking Cross-Format Table Understanding in LLMs and VLMs [50.96120467118319]
  Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly evaluated on table reasoning tasks.<n>We introduce TABVERSE, a controlled multimodal table benchmark that aligns the same table content across multiple structural formats.<n>Our results show that representation choice substantially affects table understanding.
  arXiv  Detail & Related papers  (2026-06-08T14:52:46Z)
• CRAFT: A Unified Counterfactual Reasoning Framework for Tabular Question Answering and Fact Verification [23.794030351012353]
  CRAFT is a unified Counterfactual Reasoning Framework.<n>It reformulates Tabular question answering and fact verification into a general bidirectional verification process.<n>Our approach consistently surpasses representative baselines on table reasoning datasets such as WikiTQ and TabFact.
  arXiv  Detail & Related papers  (2026-06-05T02:37:32Z)
• TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering [80.93487993878836]
  A common class of real-world queries is implicitly predictive, requiring the inference of unobserved answers from historical patterns rather than mere retrieval.<n>These queries introduce two challenges: recognizing latent intent and reliable predictive reasoning over massive tables.<n>We introduce TopBench, a benchmark consisting of 779 samples across four sub-tasks, ranging from single-point prediction to decision making, treatment effect analysis, and complex reasoning.
  arXiv  Detail & Related papers  (2026-04-30T16:22:51Z)
• ASTRA: Adaptive Semantic Tree Reasoning Architecture for Complex Table Question Answering [55.55968342644846]
  Table serialization remains a critical bottleneck for Large Language Models (LLMs) in complex table question answering.<n>Existing serialization methods fail to capture explicit hierarchies and lack schema flexibility.<n>We propose ASTRA (Adaptive Semantic Tree Reasoning Architecture) including two main modules, AdaSTR and DuTR.<n> Experiments on complex table benchmarks demonstrate that our method achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2026-04-10T06:09:41Z)
• CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrieval [12.499799382649131]
  Thought 1 (T1) is a generative retrieval model that shifts relevancemodeling from static alignment to dynamic reasoning.<n>On the query side, T1 dy-namically generates intermediate reasoning trajectories for each query to bridgeimplicit reasoning relationships.<n>On the document side, it employs an instruction+ text + embtoken> encoding format to support high- throughput indexing.
  arXiv  Detail & Related papers  (2026-03-18T06:08:59Z)
• QUIETT: Query-Independent Table Transformation for Robust Reasoning [21.03903792753972]
  Real-world tables often exhibit irregular schemas, heterogeneous value formats, and implicit relational structure.<n>We introduce QuIeTT, a query-independent table transformation framework.<n>We show consistent gains across models and reasoning paradigms, with particularly strong improvements on a challenge set of structurally diverse, unseen questions.
  arXiv  Detail & Related papers  (2026-02-23T16:23:49Z)
• Same Content, Different Representations: A Controlled Study for Table QA [15.896655757672441]
  Table Question Answering (Table QA) in real-world settings must operate over both structured databases and semi-structured tables containing textual fields.<n>Existing benchmarks are tied to fixed data formats and have not systematically examined how representation itself affects model performance.<n>We present the first controlled study that isolates the role of table representation by holding content constant while varying structure.
  arXiv  Detail & Related papers  (2025-09-26T22:33:19Z)
• LLM-Symbolic Integration for Robust Temporal Tabular Reasoning [69.27153114778748]
  We introduce TempTabQA-C, a synthetic dataset designed for systematic and controlled evaluations.<n>This structured approach allows Large Language Models (LLMs) to generate and executesql queries, enhancing generalization and mitigating biases.
  arXiv  Detail & Related papers  (2025-06-06T05:14:04Z)
• Multimodal Tabular Reasoning with Privileged Structured Information [67.40011423365712]
  We introduce TabUlar Reasoning with Bridged infOrmation (sc Turbo)<n>sc Turbo benefits from a structure-aware reasoning trace generator based on DeepSeek-R1.<n>sc Turbo achieves state-of-the-art performance ($+7.2%$ vs. previous SOTA) across multiple datasets.
  arXiv  Detail & Related papers  (2025-06-04T15:46:30Z)
• Bridging Queries and Tables through Entities in Table Retrieval [70.13748256886288]
  Entities are well-studied in the context of text retrieval, but there is a noticeable lack of research on their applications in table retrieval.<n>We propose an entity-enhanced training framework and design an interaction paradigm based on entity representations.<n>Our proposed framework is plug-and-play and flexible, making it easy to integrate into existing table retriever training processes.
  arXiv  Detail & Related papers  (2025-04-09T03:16:33Z)
• The Mighty ToRR: A Benchmark for Table Reasoning and Robustness [45.420943398134845]
  ToRR is a benchmark for Table Reasoning and Robustness, measuring model performance and robustness on table-related tasks.<n>We present a leaderboard as well as comprehensive analyses of the results of leading models over ToRR.
  arXiv  Detail & Related papers  (2025-02-26T18:56:38Z)
• HIPPO: Enhancing the Table Understanding Capability of Large Language Models through Hybrid-Modal Preference Optimization [48.240146108630704]
  This paper introduces the HybrId-modal Preference oPtimizatiOn (HIPPO) model, which represents tables using both text and image.<n> Experimental results on table question answering and table fact verification tasks demonstrate the effectiveness of HIPPO.
  arXiv  Detail & Related papers  (2025-02-24T16:50:55Z)
• ALTER: Augmentation for Large-Table-Based Reasoning [5.164923314261229]
  ALTER(Augmentation for Large-Table-Based Reasoning) is a framework designed to harness the latent augmentation potential in both free-form natural language (NL) questions. By utilizing only a small subset of relevant data from the table, ALTER achieves outstanding performance on table-based reasoning benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T12:34:45Z)
• CART: A Generative Cross-Modal Retrieval Framework with Coarse-To-Fine Semantic Modeling [53.97609687516371]
  Cross-modal retrieval aims to search for instances, which are semantically related to the query through the interaction of different modal data.<n>Traditional solutions utilize a single-tower or dual-tower framework to explicitly compute the score between queries and candidates.<n>We propose a generative cross-modal retrieval framework (CART) based on coarse-to-fine semantic modeling.
  arXiv  Detail & Related papers  (2024-06-25T12:47:04Z)
• Rethinking Tabular Data Understanding with Large Language Models [39.38132513255292]
  This study investigates the robustness of Large Language Models (LLMs) to structural perturbations in tables. We show that structural variance of tables presenting the same content reveals a notable performance decline, particularly in symbolic reasoning tasks. We conclude that the aggregation of textual and symbolic reasoning pathways, bolstered by a mix self-consistency mechanism, resulted in achieving SOTA performance, with an accuracy of 73.6% on WIKITABLEQUESTIONS.
  arXiv  Detail & Related papers  (2023-12-27T19:58:52Z)
• TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning [55.33939289989238]
  We propose TAP4LLM as a versatile pre-processor suite for leveraging large language models (LLMs) in table-based tasks effectively. It covers several distinct components: (1) table sampling to decompose large tables into manageable sub-tables based on query semantics, (2) table augmentation to enhance tables with additional knowledge from external sources or models, and (3) table packing & serialization to convert tables into various formats suitable for LLMs' understanding.
  arXiv  Detail & Related papers  (2023-12-14T15:37:04Z)
• Optimization Techniques for Unsupervised Complex Table Reasoning via Self-Training Framework [5.351873055148804]
  Self-training framework generates diverse synthetic data with complex logic. We optimize the procedure using a "Table-Text Manipulator" to handle joint table-text reasoning scenarios. UCTRST achieves above 90% of the supervised model performance on different tasks and domains.
  arXiv  Detail & Related papers  (2022-12-20T09:15:03Z)
• Table Retrieval May Not Necessitate Table-specific Model Design [83.27735758203089]
  We focus on the task of table retrieval, and ask: "is table-specific model design necessary for table retrieval?" Based on an analysis on a table-based portion of the Natural Questions dataset (NQ-table), we find that structure plays a negligible role in more than 70% of the cases. We then experiment with three modules to explicitly encode table structures, namely auxiliary row/column embeddings, hard attention masks, and soft relation-based attention biases. None of these yielded significant improvements, suggesting that table-specific model design may not be necessary for table retrieval.
  arXiv  Detail & Related papers  (2022-05-19T20:35:23Z)

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.