From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation

• URL: http://arxiv.org/abs/2512.03360v1
• Date: Wed, 03 Dec 2025 01:52:31 GMT
• Title: From Hypothesis to Premises: LLM-based Backward Logical Reasoning with Selective Symbolic Translation
• Authors: Qingchuan Li, Mingyue Cheng, Zirui Liu, Daoyu Wang, Yuting Zeng, Tongxuan Liu,
• Abstract summary: We propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR)<n>The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning.<n>HBLR consistently outperforms strong baselines in both accuracy and efficiency.
• Score: 8.104087344683604
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Logical reasoning is a core challenge in natural language understanding and a fundamental capability of artificial intelligence, underpinning scientific discovery, mathematical theorem proving, and complex decision-making. Despite the remarkable progress of large language models (LLMs), most current approaches still rely on forward reasoning paradigms, generating step-by-step rationales from premises to conclusions. However, such methods often suffer from redundant inference paths, hallucinated steps, and semantic drift, resulting in inefficient and unreliable reasoning. In this paper, we propose a novel framework, Hypothesis-driven Backward Logical Reasoning (HBLR). The core idea is to integrate confidence-aware symbolic translation with hypothesis-driven backward reasoning. In the translation phase, only high-confidence spans are converted into logical form, such as First-Order Logic (FOL), while uncertain content remains in natural language. A translation reflection module further ensures semantic fidelity by evaluating symbolic outputs and reverting lossy ones back to text when necessary. In the reasoning phase, HBLR simulates human deductive thinking by assuming the conclusion is true and recursively verifying its premises. A reasoning reflection module further identifies and corrects flawed inference steps, enhancing logical coherence. Extensive experiments on five reasoning benchmarks demonstrate that HBLR consistently outperforms strong baselines in both accuracy and efficiency.

Related papers

• Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning [50.352417879912515]
  Large language models (LLMs) excel at complex tasks with advances in reasoning capabilities.<n>We propose Group Causal Counterfactual Policy Optimization to explicitly train LLMs to learn generalizable reasoning patterns.<n>We then construct token-level advantages from this reward and optimize the policy, encouraging LLMs to favor reasoning patterns that are process-valid and counterfactually robust.
  arXiv  Detail & Related papers  (2026-02-06T08:03:11Z)
• Logical Phase Transitions: Understanding Collapse in LLM Logical Reasoning [17.5066777599458]
  Symbolic logical reasoning is a critical yet underexplored capability of large language models (LLMs)<n>We show that logical reasoning performance remains stable within a regime but collapses abruptly beyond a critical logical depth.<n>We propose Neuro-Symbolic Curriculum Tuning, a principled framework that adaptively aligns natural language with logical symbols to establish a shared representation.
  arXiv  Detail & Related papers  (2026-01-06T10:38:25Z)
• Training LLMs with LogicReward for Faithful and Rigorous Reasoning [75.30425553246177]
  We propose LogicReward, a reward system that guides model training by enforcing step-level logical correctness with a theorem prover.<n>An 8B model trained on data constructed with LogicReward surpasses GPT-4o and o4-mini by 11.6% and 2% on natural language inference and logical reasoning tasks.
  arXiv  Detail & Related papers  (2025-12-20T03:43:02Z)
• Are Language Models Efficient Reasoners? A Perspective from Logic Programming [109.47572890883248]
  Modern language models (LMs) exhibit strong deductive reasoning capabilities, yet standard evaluations emphasize correctness while overlooking a key aspect of human-like reasoning: efficiency.<n>We propose a framework for assessing LM reasoning efficiency through the lens of logic programming.
  arXiv  Detail & Related papers  (2025-10-29T15:30:31Z)
• LOGicalThought: Logic-Based Ontological Grounding of LLMs for High-Assurance Reasoning [33.30049437667383]
  High-assurance reasoning requires conclusions that are accurate, verifiable, and grounded in evidence.<n>This paper proposes a novel neurosymbolically-grounded architecture called LOGicalThought.<n>It uses an advanced logical language and reasoner in conjunction with an LLM to construct a dual symbolic graph context and logic-based context.
  arXiv  Detail & Related papers  (2025-10-02T00:06:23Z)
• From Ambiguity to Verdict: A Semiotic-Grounded Multi-Perspective Agent for LLM Logical Reasoning [16.381034926435074]
  LogicAgent is a semiotic-square-guided framework designed to jointly address logical complexity and semantic complexity.<n>To overcome the semantic simplicity and low logical complexity of existing datasets, we introduce RepublicQA, a benchmark that reaches college-level difficulty.<n>Experiments demonstrate that LogicAgent achieves state-of-the-art performance on RepublicQA, with a 6.25% average gain over strong baselines.
  arXiv  Detail & Related papers  (2025-09-29T13:31:22Z)
• DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models [58.439517684779936]
  This paper proposes a new classical logic benchmark DivLogicEval, consisting of natural sentences composed of diverse statements in a counterintuitive way.<n>To ensure a more reliable evaluation, we also introduce a new evaluation metric that mitigates the influence of bias and randomness inherent in Large Language Models.
  arXiv  Detail & Related papers  (2025-09-19T04:40:46Z)
• Reasoning is about giving reasons [55.56111618153049]
  We show that we can identify and extract the logical structure of natural language arguments in three popular reasoning datasets with high accuracies.<n>Our approach supports all forms of reasoning that depend on the logical structure of the natural language argument.
  arXiv  Detail & Related papers  (2025-08-20T07:26:53Z)
• Theorem-of-Thought: A Multi-Agent Framework for Abductive, Deductive, and Inductive Reasoning in Language Models [2.172419551358714]
  Large language models (LLMs) have shown strong performance across natural language reasoning tasks, yet their reasoning processes remain brittle and difficult to interpret.<n>We introduce Theorem-of-Thought (ToTh), a novel framework that models reasoning as collaboration among three parallel agents.<n> Experiments on symbolic (WebOfLies) and numerical (MultiArithm) reasoning benchmarks show that ToTh consistently outperforms CoT, Self-Consistency, and CoT-Decoding.
  arXiv  Detail & Related papers  (2025-06-08T12:28:38Z)
• Learning to Reason via Mixture-of-Thought for Logical Reasoning [56.24256916896427]
  Mixture-of-Thought (MoT) is a framework that enables LLMs to reason across three complementary modalities: natural language, code, and truth-table.<n>MoT adopts a two-phase design: (1) self-evolving MoT training, which jointly learns from filtered, self-generated rationales across modalities; and (2) MoT inference, which fully leverages the synergy of three modalities to produce better predictions.
  arXiv  Detail & Related papers  (2025-05-21T17:59:54Z)
• Towards Generalizable and Faithful Logic Reasoning over Natural Language via Resolution Refutation [24.584926992534346]
  We propose a novel framework, named Generalizable and Faithful Reasoner (GFaiR), which introduces the paradigm of resolution refutation. Resolution refutation has the capability to solve all first-order logic reasoning problems by extending reasoning rules and employing the principle of proof by contradiction. Our system outperforms previous works by achieving state-of-the-art performances in complex scenarios while maintaining performances in simple scenarios.
  arXiv  Detail & Related papers  (2024-04-02T06:28:44Z)

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.