LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs

• URL: http://arxiv.org/abs/2507.16809v2
• Date: Thu, 24 Jul 2025 16:51:13 GMT
• Title: LingBench++: A Linguistically-Informed Benchmark and Reasoning Framework for Multi-Step and Cross-Cultural Inference with LLMs
• Authors: Da-Chen Lian, Ri-Sheng Huang, Pin-Er Chen, Chunki Lim, You-Kuan Lin, Guan-Yu Tseng, Zi-Cheng Yang, Zhen-Yu Lin, Pin-Cheng Chen, Shu-Kai Hsieh,
• Abstract summary: LingBench++ is a benchmark and reasoning framework for evaluating large language models (LLMs)<n>It provides structured reasoning traces, stepwise evaluation protocols, and rich typological metadata across over 90 languages.<n>We show that models equipped with external knowledge sources and iterative reasoning outperform single-pass approaches in both accuracy and interpretability.
• Score: 0.631976908971572
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose LingBench++, a linguistically-informed benchmark and reasoning framework designed to evaluate large language models (LLMs) on complex linguistic tasks inspired by the International Linguistics Olympiad (IOL). Unlike prior benchmarks that focus solely on final answer accuracy, LingBench++ provides structured reasoning traces, stepwise evaluation protocols, and rich typological metadata across over 90 low-resource and cross-cultural languages. We further develop a multi-agent architecture integrating grammatical knowledge retrieval, tool-augmented reasoning, and deliberate hypothesis testing. Through systematic comparisons of baseline and our proposed agentic models, we demonstrate that models equipped with external knowledge sources and iterative reasoning outperform single-pass approaches in both accuracy and interpretability. LingBench++ offers a comprehensive foundation for advancing linguistically grounded, culturally informed, and cognitively plausible reasoning in LLMs.

Related papers

• CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models [12.52690104986201]
  We introduce the Linguistic Minimal-Pair Benchmark for evaluating constructional understanding in language models (CxMP)<n>CxMP treats form-meaning pairings, or constructions, as fundamental linguistic units.<n>Our results show that while syntactic competence emerges early, constructional understanding develops more gradually and remains limited even in large language models.
  arXiv  Detail & Related papers  (2026-02-25T14:57:23Z)
• AraLingBench A Human-Annotated Benchmark for Evaluating Arabic Linguistic Capabilities of Large Language Models [37.79823471716066]
  AraLingBench is a fully human annotated benchmark for evaluating the Arabic linguistic competence of large language models (LLMs)<n>The benchmark spans five core categories: grammar, morphology, spelling, reading comprehension, and syntax, through 150 expert-designed multiple choice questions.
  arXiv  Detail & Related papers  (2025-11-18T09:47:01Z)
• Benchmarking Chinese Commonsense Reasoning with a Multi-hop Reasoning Perspective [53.594353527056775]
  We propose Chinese Commonsense Multi-hop Reasoning ( CCMOR) to evaluate Large Language Models (LLMs)<n> CCMOR is designed to evaluate LLMs' ability to integrate Chinese-specific factual knowledge with multi-step logical reasoning.<n>We implement a human-in-the-loop verification system, where domain experts systematically validate and refine the generated questions.
  arXiv  Detail & Related papers  (2025-10-09T20:29:00Z)
• Learn Globally, Speak Locally: Bridging the Gaps in Multilingual Reasoning [38.52080213211765]
  We introduce GeoFact-X, a geography-based multilingual factual reasoning benchmark with annotated reasoning traces in five languages.<n>We propose BRIDGE, a novel training method that guides supervised fine-tuning and test-time reinforcement learning.<n>Our results show that BRIDGE significantly enhances multilingual reasoning fidelity.
  arXiv  Detail & Related papers  (2025-07-07T19:04:36Z)
• When Less Language is More: Language-Reasoning Disentanglement Makes LLMs Better Multilingual Reasoners [111.50503126693444]
  We show that language-specific ablation consistently boosts multilingual reasoning performance.<n>Compared to post-training, our training-free ablation achieves comparable or superior results with minimal computational overhead.
  arXiv  Detail & Related papers  (2025-05-21T08:35:05Z)
• Probing Large Language Models in Reasoning and Translating Complex Linguistic Puzzles [0.6144680854063939]
  This paper investigates the utilization of Large Language Models (LLMs) for solving complex linguistic puzzles.<n>Using datasets from the Puzzling Machine Competition and various Linguistics Olympiads, we employ a comprehensive set of metrics to assess the performance of GPT-4 0603.
  arXiv  Detail & Related papers  (2025-02-02T14:53:14Z)
• AdaMCoT: Rethinking Cross-Lingual Factual Reasoning through Adaptive Multilingual Chain-of-Thought [40.16140566668239]
  We introduce AdaMCOT, a framework that enhances multilingual factual reasoning.<n>AdaMCOT dynamically routing thought processes in intermediary "thinking languages" before generating target-language responses.<n>Our evaluation demonstrates substantial improvements in both factual reasoning quality and cross-lingual consistency.
  arXiv  Detail & Related papers  (2025-01-27T15:48:57Z)
• IOLBENCH: Benchmarking LLMs on Linguistic Reasoning [8.20398036986024]
  We introduce IOLBENCH, a novel benchmark derived from International Linguistics Olympiad (IOL) problems.<n>This dataset encompasses diverse problems testing syntax, morphology, phonology, and semantics.<n>We find that even the most advanced models struggle to handle the intricacies of linguistic complexity.
  arXiv  Detail & Related papers  (2025-01-08T03:15:10Z)
• The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model [59.357993924917]
  We study the evolution of multilingual capabilities in large language models (LLMs) during the pre-training process.<n>We propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities.<n>We propose a novel method to construct an optimized pre-training corpus for multilingual code LLMs.
  arXiv  Detail & Related papers  (2024-12-10T08:28:57Z)
• Large Language Models are Interpretable Learners [53.56735770834617]
  In this paper, we show a combination of Large Language Models (LLMs) and symbolic programs can bridge the gap between expressiveness and interpretability. The pretrained LLM with natural language prompts provides a massive set of interpretable modules that can transform raw input into natural language concepts. As the knowledge learned by LSP is a combination of natural language descriptions and symbolic rules, it is easily transferable to humans (interpretable) and other LLMs.
  arXiv  Detail & Related papers  (2024-06-25T02:18:15Z)
• Bridging the Bosphorus: Advancing Turkish Large Language Models through Strategies for Low-Resource Language Adaptation and Benchmarking [1.3716808114696444]
  Large Language Models (LLMs) are becoming crucial across various fields, emphasizing the urgency for high-quality models in underrepresented languages. This study explores the unique challenges faced by low-resource languages, such as data scarcity, model selection, evaluation, and computational limitations.
  arXiv  Detail & Related papers  (2024-05-07T21:58:45Z)
• Rethinking the Evaluating Framework for Natural Language Understanding in AI Systems: Language Acquisition as a Core for Future Metrics [0.0]
  In the burgeoning field of artificial intelligence (AI), the unprecedented progress of large language models (LLMs) in natural language processing (NLP) offers an opportunity to revisit the entire approach of traditional metrics of machine intelligence. Our paper proposes a paradigm shift from the established Turing Test towards an all-embracing framework that hinges on language acquisition.
  arXiv  Detail & Related papers  (2023-09-21T11:34:52Z)
• Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling [70.23876429382969]
  We propose a benchmark that can evaluate intra-sentence discourse properties across a diverse set of NLP tasks. Disco-Bench consists of 9 document-level testsets in the literature domain, which contain rich discourse phenomena. For linguistic analysis, we also design a diagnostic test suite that can examine whether the target models learn discourse knowledge.
  arXiv  Detail & Related papers  (2023-07-16T15:18:25Z)
• LERT: A Linguistically-motivated Pre-trained Language Model [67.65651497173998]
  We propose LERT, a pre-trained language model that is trained on three types of linguistic features along with the original pre-training task. We carried out extensive experiments on ten Chinese NLU tasks, and the experimental results show that LERT could bring significant improvements.
  arXiv  Detail & Related papers  (2022-11-10T05:09:16Z)
• CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark [144.05723617401674]
  General-purpose language intelligence evaluation has been a longstanding goal for natural language processing. We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic. We propose CUGE, a Chinese Language Understanding and Generation Evaluation benchmark with the following features.
  arXiv  Detail & Related papers  (2021-12-27T11:08:58Z)

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.