mlsanityData to 7 Oct 2026

Temporal Reasoning Is Not the Bottleneck: A Probabilistic Inconsistency Framework for Neuro-Symbolic QA

arXiv 2605.04243 ↗First posted 5 May 2026cs.AIcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Despite significant advances, large language models (LLMs) continue to exhibit brittle performance on complex temporal reasoning tasks. This failure mode is widely attributed to inherent deficits in autoregressive logical deduction. In this paper, we challenge this prevailing narrative, demonstrating that temporal reasoning is not the fundamental bottleneck; rather, the locus of failure lies in unstructured text-to-event representation. We introduce a novel neuro-symbolic question-answering framework governed by a Probabilistic Inconsistency Signal (PIS) that explicitly isolates perceptual errors from reasoning failures. By lifting unstructured text into explicit event graphs and interval constraints, our architecture strictly decouples semantic extraction from a symbolic reasoning engine. To robustly detect structural breaks, the PIS elegantly unifies symbolic credal intervals with epistemic neural uncertainty extracted via Evidential Deep Learning on LLM hidden states. Empirical evaluations reveal a striking paradigm shift: when provided with correct structural representations, our system's explicit proof traces achieve perfect 1.0 accuracy (4000/4000) and strictly zero false positives/negatives on temporal arithmetic benchmarks. On broader, noise-injected QA settings, the framework maintains a competitive 75.1% accuracy while enabling deterministic, step-level failure localization. Ultimately, by isolating the representation bottleneck from the reasoning substrate, this work reframes temporal QA from an algorithmic reasoning challenge to a structural alignment problem, charting a verifiable path forward for reliable neuro-symbolic AI.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 50 of its 86 references that are in the map. First posted on arXiv 5 May 2026.

Builds on

50 of 86 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debate23 May
  2. 2022Towards Reasoning in Large Language Models: A Survey20 Dec
  3. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning19 May
  4. 2022Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?25 Feb
  5. 2021Show Your Work: Scratchpads for Intermediate Computation with Language Models30 Nov

Other references · 45

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2022Training language models to follow instructions with human feedbackcited by 15,712
  5. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  6. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  7. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  8. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  9. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  10. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  11. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,203
  12. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
33 more
  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  2. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  3. 2021Convex optimizationcited by 2,479
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2022Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language modelscited by 1,970
  7. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  8. 2022Language Models (Mostly) Know What They Knowcited by 1,783
  9. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,359
  10. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  11. 2021Scaling Language Models: Methods, Analysis & Insights from Training Gophercited by 1,199
  12. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  13. 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 979
  14. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  15. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 946
  16. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  17. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  18. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  19. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  20. 2019Neural Probabilistic Logic Programming in DeepProbLogcited by 389
  21. 2019FinBERT: Financial Sentiment Analysis with Pre-trained Language Modelscited by 378
  22. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Changecited by 372
  23. 2019Deep Evidential Regressioncited by 354
  24. 2017Neural-Symbolic Learning and Reasoning: A Survey and Interpretationcited by 195
  25. 2020Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Countscited by 163
  26. 2021Explaining Answers with Entailment Treescited by 148
  27. 2019Neural Logic Machinescited by 144
  28. 2018emrQA: A Large Corpus for Question Answering on Electronic Medical Recordscited by 134
  29. 2020Logical Neural Networkscited by 118
  30. 2022Neuro-Symbolic Language Modeling with Automaton-augmented Retrievalcited by 60
  31. 2020Temporal Reasoning on Implicit Events from Distant Supervisioncited by 58
  32. 2020Reliable Graph Neural Networks via Robust Aggregationcited by 43
  33. 2023Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Modelscited by 37

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025NeSTR: A Neuro-Symbolic Abductive Framework for Temporal Reasoning in Large Language Models
  2. 2026STAIR: Semantic-Temporal Automaton for Interpretable Reasoning in Temporal Question Answering
  3. 2024Reliable Reasoning Beyond Natural Language
  4. 2026ReEfBench: Quantifying the Reasoning Efficiency of LLMs
  5. 2022NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning
  6. 2026BaziQA-Benchmark: Evaluating Symbolic and Temporally Compositional Reasoning in Large Language Models
  7. 2025LTLZinc: a Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning
  8. 2025FactReasoner: A Probabilistic Approach to Long-Form Factuality Assessment for Large Language Models