Multi-Step Reasoning in Korean and the Emergent Mirage

• URL: http://arxiv.org/abs/2501.05712v2
• Date: Wed, 12 Mar 2025 08:45:28 GMT
• Title: Multi-Step Reasoning in Korean and the Emergent Mirage
• Authors: Guijin Son, Hyunwoo Ko, Dasol Choi,
• Abstract summary: We introduce HRMCR (HAE-RAE Multi-Step Commonsense Reasoning), a benchmark designed to evaluate large language models' ability to perform multi-step reasoning in culturally specific contexts.<n>The questions are automatically generated via templates and algorithms, requiring LLMs to integrate Korean cultural knowledge into sequential reasoning steps.<n>Our experiments reveal that models trained on fewer than (2 cdot 1025) training FLOPs struggle to solve any questions, showing near-zero performance.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We introduce HRMCR (HAE-RAE Multi-Step Commonsense Reasoning), a benchmark designed to evaluate large language models' ability to perform multi-step reasoning in culturally specific contexts, focusing on Korean. The questions are automatically generated via templates and algorithms, requiring LLMs to integrate Korean cultural knowledge into sequential reasoning steps. Consistent with prior observations on emergent abilities, our experiments reveal that models trained on fewer than \(2 \cdot 10^{25}\) training FLOPs struggle to solve any questions, showing near-zero performance. Beyond this threshold, performance improves sharply. State-of-the-art models (e.g., O1) still score under 50\%, underscoring the difficulty of our tasks. Notably, stepwise analysis suggests the observed emergent behavior may stem from compounding errors across multiple steps rather than reflecting a genuinely new capability. We publicly release the benchmark and commit to regularly updating the dataset to prevent contamination.

Related papers

• RefineBench: Evaluating Refinement Capability of Language Models via Checklists [71.02281792867531]
  We evaluate two refinement modes: guided refinement and self-refinement.<n>In guided refinement, both proprietary LMs and large open-weight LMs can leverage targeted feedback to refine responses to near-perfect levels within five turns.<n>These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses.
  arXiv  Detail & Related papers  (2025-11-27T07:20:52Z)
• Can an Easy-to-Hard Curriculum Make Reasoning Emerge in Small Language Models? Evidence from a Four-Stage Curriculum on GPT-2 [0.8423417997128777]
  We demonstrate that a developmentally ordered curriculum markedly improves reasoning transparency and sample-efficiency in small language models.<n>We identify challenges: final-answer success still lags a conventional run by about 30%, and our saliency probe under-detects verbal-knowledge heads in the hardest stage.
  arXiv  Detail & Related papers  (2025-05-16T19:08:31Z)
• Redefining Evaluation Standards: A Unified Framework for Evaluating the Korean Capabilities of Language Models [0.0]
  We introduce HRET (Haerae Evaluation Toolkit), an open-source, registry-based framework that unifies Korean assessment.<n>HRET integrates major Korean benchmarks, multiple inference backends, and multi-method evaluation.<n>Its modular registry design also enables rapid incorporation of new datasets, methods, and backends.
  arXiv  Detail & Related papers  (2025-03-29T04:17:58Z)
• LINGOLY-TOO: Disentangling Memorisation from Reasoning with Linguistic Templatisation and Orthographic Obfuscation [1.2576388595811496]
  We introduce a framework for producing linguistic reasoning problems that reduces the effect of memorisation in model performance estimates. We apply this framework to develop LINGOLY-TOO, a challenging benchmark for linguistic reasoning.
  arXiv  Detail & Related papers  (2025-03-04T19:57:47Z)
• Multilingual European Language Models: Benchmarking Approaches and Challenges [2.413212225810367]
  generative large language models (LLMs) can solve different tasks through chat interaction. This paper analyses the benefits and limitations of current evaluation datasets, focusing on multilingual European benchmarks. We discuss potential solutions to enhance translation quality and cultural biases, including human-in-the-loop verification and iterative translation ranking.
  arXiv  Detail & Related papers  (2025-02-18T14:32:17Z)
• Demystifying Multilingual Chain-of-Thought in Process Reward Modeling [71.12193680015622]
  We tackle the challenge of extending process reward models (PRMs) to multilingual settings. We train multilingual PRMs on a dataset spanning seven languages, which is translated from English. Our results highlight the sensitivity of multilingual PRMs to both the number of training languages and the volume of English data.
  arXiv  Detail & Related papers  (2025-02-18T09:11:44Z)
• LlamaV-o1: Rethinking Step-by-step Visual Reasoning in LLMs [103.0226977561914]
  We propose a comprehensive framework for advancing step-by-step visual reasoning in large language models. We introduce a visual reasoning benchmark specifically designed to evaluate multi-step reasoning tasks. Second, we propose a novel metric that assesses visual reasoning quality at the granularity of individual steps. Third, we present a new multimodal visual reasoning model, named LlamaV-o1, trained using a multi-step curriculum learning approach.
  arXiv  Detail & Related papers  (2025-01-10T18:59:51Z)
• Self-Evolving Critique Abilities in Large Language Models [59.861013614500024]
  This paper explores enhancing critique abilities of Large Language Models (LLMs)<n>We introduce SCRIT, a framework that trains LLMs with self-generated data to evolve their critique abilities.<n>Our analysis reveals that SCRIT's performance scales positively with data and model size.
  arXiv  Detail & Related papers  (2025-01-10T05:51:52Z)
• Understand, Solve and Translate: Bridging the Multilingual Mathematical Reasoning Gap [0.0]
  Large language models (LLMs) demonstrate exceptional performance on complex reasoning tasks.<n>Despite strong reasoning capabilities in high-resource languages, a significant performance gap persists in other languages.<n>We propose UST (Understand, Solve, and Translate), a method that strategically uses English as an anchor for reasoning and solution generation.
  arXiv  Detail & Related papers  (2025-01-05T05:57:22Z)
• Unconditional Truthfulness: Learning Unconditional Uncertainty of Large Language Models [104.55763564037831]
  We train a regression model that leverages attention maps, probabilities on the current generation step, and recurrently computed uncertainty scores from previously generated tokens.<n>Our evaluation shows that the proposed method is highly effective for selective generation, achieving substantial improvements over rivaling unsupervised and supervised approaches.
  arXiv  Detail & Related papers  (2024-08-20T09:42:26Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making.<n>We present a process-based benchmark MR-Ben that demands a meta-reasoning skill.<n>Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning [47.75550640881761]
  We explore cross-lingual generalization in instruction tuning by applying it to non-English tasks. We design cross-lingual templates to mitigate discrepancies in language and instruction-format of the template between training and inference. Our experiments reveal consistent improvements through cross-lingual generalization in both English and Korean.
  arXiv  Detail & Related papers  (2024-06-13T04:10:17Z)
• The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
  We propose a question alignment framework to bridge the gap between large language models' English and non-English performance. Experiment results show it can boost multilingual performance across diverse reasoning scenarios, model families, and sizes. We analyze representation space, generated response and data scales, and reveal how question translation training strengthens language alignment within LLMs.
  arXiv  Detail & Related papers  (2024-05-02T14:49:50Z)
• Min-K%++: Improved Baseline for Detecting Pre-Training Data from Large Language Models [15.50128790503447]
  We propose a novel and theoretically motivated methodology for pre-training data detection, named Min-K%++. Specifically, we present a key insight that training samples tend to be local maxima of the modeled distribution along each input dimension through likelihood training.
  arXiv  Detail & Related papers  (2024-04-03T04:25:01Z)
• CIF-Bench: A Chinese Instruction-Following Benchmark for Evaluating the Generalizability of Large Language Models [53.9835961434552]
  We introduce the Chinese Instruction-Following Benchmark (CIF-Bench) to evaluate the generalizability of large language models (LLMs) to the Chinese language. CIF-Bench comprises 150 tasks and 15,000 input-output pairs, developed by native speakers to test complex reasoning and Chinese cultural nuances. To mitigate data contamination, we release only half of the dataset publicly, with the remainder kept private, and introduce diversified instructions to minimize score variance.
  arXiv  Detail & Related papers  (2024-02-20T16:02:12Z)
• Information Association for Language Model Updating by Mitigating LM-Logical Discrepancy [68.31760483418901]
  Large Language Models(LLMs) struggle with providing current information due to the outdated pre-training data. Existing methods for updating LLMs, such as knowledge editing and continual fine-tuning, have significant drawbacks in generalizability of new information. We identify the core challenge behind these drawbacks: the LM-logical discrepancy featuring the difference between language modeling probabilities and logical probabilities.
  arXiv  Detail & Related papers  (2023-05-29T19:48:37Z)

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.