arXiv subjects

Naoaki Okazaki

Publications and source records attributed to Naoaki Okazaki.

At least 37 records · Page 2Linked to original sources

arXiv2026

JaWildText: A Benchmark for Vision-Language Models on Japanese Scene Text Understanding

Japanese scene text poses challenges that multilingual benchmarks often fail to capture, including mixed scripts, frequent vertical writing, and a character inventory far larger than the Latin alphabet. Although Japanese is included in several multilingual benchmarks, these resources do not adequately capture the language-specific complexities. Meanwhile, existing Japanese visual text datasets have primarily focused on scanned documents, leaving in-the-wild scene text underexplored. To fill this gap, we introduce JaWildText, a diagnostic benchmark for evaluating vision-language models (VLMs) on Japanese scene text understanding. JaWildText contains 3,241 instances from 2,961 images newly captured in Japan, with 1.12 million annotated characters spanning 3,643 unique character types. It comprises three complementary tasks that vary in visual organization, output format, and writing style: (i) Dense Scene Text Visual Question Answering (STVQA), which requires reasoning over multiple pieces of visual text evidence; (ii) Receipt Key Information Extraction (KIE), which tests layout-aware structured extraction from mobile-captured receipts; and (iii) Handwriting OCR, which evaluates page-level transcription across various media and writing directions. We evaluate 14 open-weight VLMs and find that the best model achieves an average score of 0.64 across the three tasks. Error analyses show recognition remains the dominant bottleneck, especially for kanji. JaWildText enables fine-grained, script-aware diagnosis of Japanese scene text capabilities, and will be released with evaluation code.

cs.CV↗

arXiv2026

JUBAKU: An Adversarial Benchmark for Exposing Culturally Grounded Stereotypes in Japanese LLMs

Social biases reflected in language are inherently shaped by cultural norms, which vary significantly across regions and lead to diverse manifestations of stereotypes. Existing evaluations of social bias in large language models (LLMs) for non-English contexts, however, often rely on translations of English benchmarks. Such benchmarks fail to reflect local cultural norms, including those found in Japanese. For instance, Western benchmarks may overlook Japan-specific stereotypes related to hierarchical relationships, regional dialects, or traditional gender roles. To address this limitation, we introduce Japanese cUlture adversarial BiAs benchmarK Under handcrafted creation (JUBAKU), a benchmark tailored to Japanese cultural contexts. JUBAKU uses adversarial construction to expose latent biases across ten distinct cultural categories. Unlike existing benchmarks, JUBAKU features dialogue scenarios hand-crafted by native Japanese annotators, specifically designed to trigger and reveal latent social biases in Japanese LLMs. We evaluated nine Japanese LLMs on JUBAKU and three others adapted from English benchmarks. All models clearly exhibited biases on JUBAKU, performing below the random baseline of 50% with an average accuracy of 23% (ranging from 13% to 33%), despite higher accuracy on the other benchmarks. Human annotators achieved 91% accuracy in identifying unbiased responses, confirming JUBAKU's reliability and its adversarial nature to LLMs.

cs.CL↗

arXiv2026

Multi-modal, Multi-task, Multi-criteria Automatic Evaluation with Vision Language Models

Vision-language models (VLMs) have shown impressive abilities across a range of multi-modal tasks. However, existing metrics for evaluating the quality of text generated by VLMs typically focus on an overall evaluation for a specific task, such as image captioning. While the overall evaluation is essential for any task, the criteria prioritized can differ depending on the task, making it challenging for current metrics to adapt to multi-task scenarios. To address this limitation, we propose HarmonicEval, a reference-free comprehensive evaluation metric that aggregates criterion-wise scores to produce the overall score in a bottom-up manner. Furthermore, to assess the generalizability of automatic evaluation metrics in multi-task scenarios, we construct the Multi-task Multi-criteria Human Evaluation (MMHE) benchmark, which comprises 18,000 expert human judgments across four multi-modal tasks. Our experiments demonstrate that HarmonicEval achieves higher correlations with human judgments than conventional metrics while providing numerical scores for each criterion. Project page: https://stjohn2007.github.io/MMHE_project/

cs.CL↗

arXiv2026

Rewriting Pre-Training Data Boosts LLM Performance in Math and Code

The performance of large language models (LLMs) in program synthesis and mathematical reasoning is fundamentally limited by the quality of their pre-training corpora. We introduce two openly licensed pre-training datasets, released under the Llama 3.3 Community License, that significantly enhance LLM performance by systematically rewriting public data. SwallowCode ($\approx$16.1 billion tokens) refines Python snippets from The-Stack-v2 through a novel four-stage pipeline: syntax validation, pylint-based style filtering, and a two-stage LLM rewriting process that enforces style conformity and transforms snippets into self-contained, algorithmically efficient examples. Unlike prior methods that rely on exclusionary filtering or limited transformations, our transform-and-retain approach refines low-quality code, maximizing data utility. SwallowMath ($\approx$2.3 billion tokens) enhances Finemath-4+ by removing boilerplate, restoring context, and reformatting solutions into concise, step-by-step explanations. Within a fixed 50 billion token training budget, continual pre-training of Llama-3.1-8B with SwallowCode boosts pass@1 by +17.0 on HumanEval and +16.1 on HumanEval+ compared to Stack-Edu, surpassing the baseline model's code generation capabilities. Similarly, substituting SwallowMath yields +12.4 accuracy on GSM8K and +7.6 on MATH. Ablation studies confirm that each pipeline stage contributes incrementally, with rewriting yielding the largest gains. By releasing datasets, prompts, checkpoints, and pipeline code, we ensure reproducibility and provide a transferable transform-and-retain methodology that can be adapted to other base models and LLM rewriting setups.

cs.LG↗

arXiv2026

Machine Text Detectors are Membership Inference Attacks

Although membership inference attacks (MIAs) and machine-generated text detection target different goals, their methods often exploit similar signals based on a language model's probability distribution, and the two tasks have been studied independently. This can result in conclusions that overlook stronger methods and valuable insights from the other task. In this work, we theoretically and empirically demonstrate the transferability, i.e., how well a method originally developed for one task performs on the other, between MIAs and machine text detection. We prove that the metric achieving asymptotically optimal performance is identical for both tasks. We unify existing methods under this optimal metric and hypothesize that the accuracy with which a method approximates this metric is directly correlated with its transferability. Our large-scale empirical experiments demonstrate very strong rank correlation ($ρ\approx 0.7$) in cross-task performance. Notably, we also find that a machine text detector achieves the strongest performance among evaluated methods on both tasks, demonstrating the practical impact of transferability. To facilitate cross-task development and fair evaluation, we introduce MINT, a unified evaluation suite for MIAs and machine-generated text detection, implementing 15 recent methods from both tasks.

cs.CL↗

arXiv2025

Likelihood-based Mitigation of Evaluation Bias in Large Language Models

Large Language Models (LLMs) are widely used to evaluate natural language generation tasks as automated metrics. However, the likelihood, a measure of LLM's plausibility for a sentence, can vary due to superficial differences in sentences, such as word order and sentence structure. It is therefore possible that there might be a likelihood bias if LLMs are used for evaluation: they might overrate sentences with higher likelihoods while underrating those with lower likelihoods. In this paper, we investigate the presence and impact of likelihood bias in LLM-based evaluators. We also propose a method to mitigate the likelihood bias. Our method utilizes highly biased instances as few-shot examples for in-context learning. Our experiments in evaluating the data-to-text and grammatical error correction tasks reveal that several LLMs we test display a likelihood bias. Furthermore, our proposed method successfully mitigates this bias, also improving evaluation performance (in terms of correlation of models with human scores) significantly.

cs.CL↗

arXiv2025

QuantumBench: A Benchmark for Quantum Problem Solving

Large language models are now integrated into many scientific workflows, accelerating data analysis, hypothesis generation, and design space exploration. In parallel with this growth, there is a growing need to carefully evaluate whether models accurately capture domain-specific knowledge and notation, since general-purpose benchmarks rarely reflect these requirements. This gap is especially clear in quantum science, which features non-intuitive phenomena and requires advanced mathematics. In this study, we introduce QuantumBench, a benchmark for the quantum domain that systematically examine how well LLMs understand and can be applied to this non-intuitive field. Using publicly available materials, we compiled approximately 800 questions with their answers spanning nine areas related to quantum science and organized them into an eight-option multiple-choice dataset. With this benchmark, we evaluate several existing LLMs and analyze their performance in the quantum domain, including sensitivity to changes in question format. QuantumBench is the first LLM evaluation dataset built for the quantum domain, and it is intended to guide the effective use of LLMs in quantum research.

cs.AI↗

arXiv2025

Decoding-Free Sampling Strategies for LLM Marginalization

Modern language models operate on subword-tokenized text in order to make a trade-off between model size, inference speed, and vocabulary coverage. A side effect of this is that, during inference, models are evaluated by measuring the probability of only the specific tokenization produced as the output, despite there being many possible ways to represent the same text with a subword vocabulary. Recent studies have argued instead for evaluating LLMs by marginalization - the probability mass of all tokenizations of a given text. Marginalization is difficult due to the number of possible tokenizations of a text, so often approximate marginalization is done via sampling. However, a downside of sampling is that an expensive generation step must be performed by the LLM for each sample, which limits the number of samples that can be acquired given a runtime budget, and therefore also the accuracy of the approximation. Since computing the probability of a sequence given the tokenization is relatively cheap compared to actually generating it, we investigate sampling strategies that are decoding-free - they require no generation from the LLM, instead relying entirely on extremely cheap sampling strategies that are model and tokenizer agnostic. We investigate the approximation quality and speed of decoding-free sampling strategies for a number of open models to find that they provide sufficiently accurate marginal estimates at a small fraction of the runtime cost and demonstrate its use on a set of downstream inference tasks.

cs.CL↗

arXiv2025

Why We Build Local Large Language Models: An Observational Analysis from 35 Japanese and Multilingual LLMs

Why do we build local large language models (LLMs)? What should a local LLM learn from the target language? Which abilities can be transferred from other languages? Do language-specific scaling laws exist? To explore these research questions, we evaluated 35 Japanese, English, and multilingual LLMs on 19 evaluation benchmarks for Japanese and English, taking Japanese as a local language. Adopting an observational approach, we analyzed correlations of benchmark scores, and conducted principal component analysis (PCA) on the scores to derive \textit{ability factors} of local LLMs. We found that training on English text can improve the scores of academic subjects in Japanese (JMMLU). In addition, it is unnecessary to specifically train on Japanese text to enhance abilities for solving Japanese code generation, arithmetic reasoning, commonsense, and reading comprehension tasks. In contrast, training on Japanese text could improve question-answering tasks about Japanese knowledge and English-Japanese translation, which indicates that abilities for solving these two tasks can be regarded as \textit{Japanese abilities} for LLMs. Furthermore, we confirmed that the Japanese abilities scale with the computational budget for Japanese text.

cs.CL↗

arXiv2025

Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models

Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction approach can be easily adapted to other languages; we build datasets for Japanese and confirm that LLMs tuned with our data reach state-of-the-art performance. Analyses suggest that instruction-tuning in a new language allows LLMs to follow instructions, while the tuned models exhibit a notable lack of culture-specific knowledge in that language. The datasets and fine-tuned models will be publicly available. Our datasets, synthesized with open-weight LLMs, are openly distributed under permissive licenses, allowing for diverse use cases.

cs.CL↗

arXiv2025

Bit-level BPE: Below the byte boundary

Byte-level fallbacks for subword tokenization have become a common practice in large language models. In particular, it has been demonstrated to be incredibly effective as a pragmatic solution for preventing OOV, especially in the context of larger models. However, breaking a character down to individual bytes significantly increases the sequence length for long-tail tokens in languages such as Chinese, Japanese, and Korean (CJK) and other character-diverse contexts such as emoji. The increased sequence length results in longer computation during both training and inference. In this work, we propose a simple compression technique that reduces the sequence length losslessly.

cs.CL↗

arXiv2025

Intent-Aware Self-Correction for Mitigating Social Biases in Large Language Models

Self-Correction based on feedback improves the output quality of Large Language Models (LLMs). Moreover, as Self-Correction functions like the slow and conscious System-2 thinking from cognitive psychology's perspective, it can potentially reduce LLMs' social biases. LLMs are sensitive to contextual ambiguities and inconsistencies; therefore, explicitly communicating their intentions during interactions when applying Self-Correction for debiasing is crucial. In this study, we demonstrate that clarifying intentions is essential for effectively reducing biases in LLMs through Self-Correction. We divide the components needed for Self-Correction into three parts: instruction, response, and feedback, and clarify intentions at each component. We incorporate an explicit debiasing prompt to convey the intention of bias mitigation from the instruction for response generation. In the response, we use Chain-of-Thought (CoT) to clarify the reasoning process. In the feedback, we define evaluation aspects necessary for debiasing and propose clear feedback through multi-aspect critiques and scoring. Through experiments, we demonstrate that self-correcting CoT responses obtained from a debiasing prompt based on multi-aspect feedback can reduce biased responses more robustly and consistently than the baselines. We also find the variation in debiasing efficacy when using models with different bias levels or separating models for response and feedback generation.

cs.CL↗

arXiv2025

LCTG Bench: LLM Controlled Text Generation Benchmark

The rise of large language models (LLMs) has led to more diverse and higher-quality machine-generated text. However, their high expressive power makes it difficult to control outputs based on specific business instructions. In response, benchmarks focusing on the controllability of LLMs have been developed, but several issues remain: (1) They primarily cover major languages like English and Chinese, neglecting low-resource languages like Japanese; (2) Current benchmarks employ task-specific evaluation metrics, lacking a unified framework for selecting models based on controllability across different use cases. To address these challenges, this research introduces LCTG Bench, the first Japanese benchmark for evaluating the controllability of LLMs. LCTG Bench provides a unified framework for assessing control performance, enabling users to select the most suitable model for their use cases based on controllability. By evaluating nine diverse Japanese-specific and multilingual LLMs like GPT-4, we highlight the current state and challenges of controllability in Japanese LLMs and reveal the significant gap between multilingual models and Japanese-specific models.

cs.CL↗

arXiv2024

LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs

This paper introduces LLM-jp, a cross-organizational project for the research and development of Japanese large language models (LLMs). LLM-jp aims to develop open-source and strong Japanese LLMs, and as of this writing, more than 1,500 participants from academia and industry are working together for this purpose. This paper presents the background of the establishment of LLM-jp, summaries of its activities, and technical reports on the LLMs developed by LLM-jp. For the latest activities, visit https://llm-jp.nii.ac.jp/en/.

cs.CL↗

arXiv2024

Constructing Multimodal Datasets from Scratch for Rapid Development of a Japanese Visual Language Model

To develop high-performing Visual Language Models (VLMs), it is essential to prepare multimodal resources, such as image-text pairs, interleaved data, and instruction data. While multimodal resources for English are abundant, there is a significant lack of corresponding resources for non-English languages, such as Japanese. To address this problem, we take Japanese as a non-English language and propose a method for rapidly creating Japanese multimodal datasets from scratch. We collect Japanese image-text pairs and interleaved data from web archives and generate Japanese instruction data directly from images using an existing VLM. Our experimental results show that a VLM trained on these native datasets outperforms those relying on machine-translated content.

cs.CL↗

arXiv2024

Tokenization as Finite-State Transduction

Tokenization is the first step in modern neural language model pipelines where an input text is converted to a sequence of subword tokens. We introduce from first principles a finite-state transduction framework which can efficiently encode all possible tokenizations of a regular language. We then constructively show that Byte-Pair Encoding (BPE) and MaxMatch (WordPiece), two popular tokenization schemes, fit within this framework. For BPE, this is particularly surprising given its resemblance to context-free grammar and the fact that it does not tokenize strings from left to right. An application of this is to guided generation, where the outputs of a language model are constrained to match some pattern. Here, patterns are encoded at the character level, which creates a mismatch between the constraints and the model's subword vocabulary. While past work has focused only on constraining outputs without regard to the underlying tokenization algorithm, our framework allows for simultaneously constraining the model outputs to match a specified pattern while also adhering to the underlying tokenizer's canonical tokenization.

cs.CL↗

arXiv2024

How You Prompt Matters! Even Task-Oriented Constraints in Instructions Affect LLM-Generated Text Detection

To combat the misuse of Large Language Models (LLMs), many recent studies have presented LLM-generated-text detectors with promising performance. When users instruct LLMs to generate texts, the instruction can include different constraints depending on the user's need. However, most recent studies do not cover such diverse instruction patterns when creating datasets for LLM detection. In this paper, we reveal that even task-oriented constraints -- constraints that would naturally be included in an instruction and are not related to detection-evasion -- cause existing powerful detectors to have a large variance in detection performance. We focus on student essay writing as a realistic domain and manually create task-oriented constraints based on several factors for essay quality. Our experiments show that the standard deviation (SD) of current detector performance on texts generated by an instruction with such a constraint is significantly larger (up to an SD of 14.4 F1-score) than that by generating texts multiple times or paraphrasing the instruction. We also observe an overall trend where the constraints can make LLM detection more challenging than without them. Finally, our analysis indicates that the high instruction-following ability of LLMs fosters the large impact of such constraints on detection performance.

cs.CL↗

arXiv2024

Distributional Properties of Subword Regularization

Subword regularization, used widely in NLP, improves model performance by reducing the dependency on exact tokenizations, augmenting the training corpus, and exposing the model to more unique contexts during training. BPE and MaxMatch, two popular subword tokenization schemes, have stochastic dropout regularization variants. However, there has not been an analysis of the distributions formed by them. We show that these stochastic variants are heavily biased towards a small set of tokenizations per word. If the benefits of subword regularization are as mentioned, we hypothesize that biasedness artificially limits the effectiveness of these schemes. Thus, we propose an algorithm to uniformly sample tokenizations that we use as a drop-in replacement for the stochastic aspects of existing tokenizers, and find that it improves machine translation quality.

cs.CL↗