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.

Logical reasoning with large language models (LLMs) has received growing attention. One mainstream approach translates natural language into formal logic and then applies symbolic solvers for deduction. While effective in many tasks, these LLM-based translators often fail to generate consistent symbolic representations when the same concept appears in different linguistic forms. Such inconsistencies break logical coherence and lead to solver errors. However, most existing benchmarks lack this type of linguistic variation, which frequently occurs in real-world text, leaving the problem underexplored. To address this gap, we present SoLT, a benchmark that systematically rewrites reasoning datasets into diverse yet logically equivalent forms across multiple levels. Beyond evaluation, SoLT also provides a general method to enrich any dataset with linguistic diversity while preserving both meaning and logic. To further enhance the stability of LLM-based reasoning, we propose MenTaL, which explicitly guides models to build a concept–symbol mapping table during translation. By linking equivalent expressions to shared symbols, MenTaL maintains consistency and mitigates symbol drift. Experiments on SoLT demonstrate that LLMs indeed suffer from inconsistent symbol mapping under linguistic variation, leading to significant drops in reasoning accuracy. Meanwhile, applying MenTaL brings clear and stable performance improvements across diverse inputs. Overall, our findings reveal that overlooking linguistic diversity hides key weaknesses in LLM-based translators, and our work offers a step toward more reliable logical reasoning in varied real-world scenarios. Our code is available at https://github.com/wufeiwuwoshihua/LinguDiver.

Large Vision-Language Models (LVLMs) achieve remarkable performance in multimodal tasks but suffer from high computational costs due to the large number of visual tokens.Existing pruning methods either apply after visual tokens enter the LLM or perform pre-pruning based solely on visual attention.Both fail to balance efficiency and semantic alignment, as post-pruning incurs redundant computation, while visual-only pre-pruning overlooks multimodal relevance.To address this limitation, we propose Dual-Cue Pruning (DCP), a novel cross-modal pruning framework that jointly considers textual semantics and visual selfattention.DCP consists of a text-aware computation module, which employs a gradientweighted attention mechanism to enhance textvisual alignment, and an image-aware computation module, which utilizes deep-layer selfattention distributions to retain essential structural information.By integrating both cues, DCP adaptively selects the most informative visual tokens, achieving efficient inference acceleration while maintaining strong task performance.Experimental results show that DCP can retain only 25% of the visual tokens, with a minimal performance degradation of 0.063% on LLaVA-1.5-13B,demonstrating its effectiveness in balancing efficiency and accuracy.

Tongxuan Liu, Wenjiang Xu, Weizhe Huang, Yuting Zeng, Jiaxing Wang, Xingyu Wang, Hailong Yang, Jing Li. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.