arXiv subjects

Hidetaka Kamigaito

Publications and source records attributed to Hidetaka Kamigaito.

At least 37 records · Page 2Linked to original sources

arXiv2026

XQ-MEval: A Dataset with Cross-lingual Parallel Quality for Benchmarking Translation Metrics

Automatic evaluation metrics are essential for building multilingual translation systems. The common practice of evaluating these systems is averaging metric scores across languages, yet this is suspicious since metrics may suffer from cross-lingual scoring bias, where translations of equal quality receive different scores across languages. This problem has not been systematically studied because no benchmark exists that provides parallel-quality instances across languages, and expert annotation is not realistic. In this work, we propose XQ-MEval, a semi-automatically built dataset covering nine translation directions, to benchmark translation metrics. Specifically, we inject MQM-defined errors into gold translations automatically, filter them by native speakers for reliability, and merge errors to generate pseudo translations with controllable quality. These pseudo translations are then paired with corresponding sources and references to form triplets used in assessing the qualities of translation metrics. Using XQ-MEval, our experiments on nine representative metrics reveal the inconsistency between averaging and human judgment and provide the first empirical evidence of cross-lingual scoring bias. Finally, we propose a normalization strategy derived from XQ-MEval that aligns score distributions across languages, improving the fairness and reliability of multilingual metric evaluation.

cs.CL↗

arXiv2026

TextTIGER: Text-based Intelligent Generation with Entity Prompt Refinement for Text-to-Image Generation

When generating images from prompts that include specific entities, the model must retain as much entity-specific knowledge as possible. However, the number of entities is almost countless, and new entities emerge; memorizing all of them completely is not realistic. To bridge this gap, our work proposes Text-based Intelligent Generation with Entity Prompt Refinement (TextTIGER). TextTIGER strengthens knowledge about entities that appear in the prompt by augmenting external information and then summarizes the expanded descriptions with large language models, preventing performance degradation that arises from excessively long inputs. To evaluate our method, we construct a new dataset consisting of captions, images, detailed descriptions, and lists of entities. Experiments with multiple image generation models show that TextTIGER improves image generation performance on widely used evaluation metrics compared with prompts that use captions alone. In addition, using Multimodal LLM (MLLM)-as-a-judge, which shows a strong correlation with human evaluation, we demonstrate that our method consistently achieves higher scores, which underscores its effectiveness. These results show that strengthening entity-related descriptions, summarizing them, and refining prompts to an appropriate length leads to substantial improvements in image generation performance. We will release the created dataset and code upon acceptance.

cs.CL↗

arXiv2026

Identifying Influential N-grams in Confidence Calibration via Regression Analysis

While large language models (LLMs) improve performance by explicit reasoning, their responses are often overconfident, even though they include linguistic expressions demonstrating uncertainty. In this work, we identify what linguistic expressions are related to confidence by applying the regression method. Specifically, we predict confidence of those linguistic expressions in the reasoning parts of LLMs as the dependent variables and analyze the relationship between a specific $n$-gram and confidence. Across multiple models and QA benchmarks, we show that LLMs remain overconfident when reasoning is involved and attribute this behavior to specific linguistic information. Interestingly, several of the extracted expressions coincide with cue phrases intentionally inserted on test-time scaling to improve reasoning performance. Through our test on causality and verification that the extracted linguistic information truly affects confidence, we reveal that confidence calibration is possible by simply suppressing those overconfident expressions without drops in performance.

cs.CL↗

arXiv2026

CodeNER: Code Prompting for Named Entity Recognition

Recent studies have explored various approaches for treating candidate named entity spans as both source and target sequences in named entity recognition (NER) by leveraging large language models (LLMs). Although previous approaches have successfully generated candidate named entity spans with suitable labels, they rely solely on input context information when using LLMs, particularly, ChatGPT. However, NER inherently requires capturing detailed labeling requirements with input context information. To address this issue, we propose a novel method that leverages code-based prompting to improve the capabilities of LLMs in understanding and performing NER. By embedding code within prompts, we provide detailed BIO schema instructions for labeling, thereby exploiting the ability of LLMs to comprehend long-range scopes in programming languages. Experimental results demonstrate that the proposed code-based prompting method outperforms conventional text-based prompting on ten benchmarks across English, Arabic, Finnish, Danish, and German datasets, indicating the effectiveness of explicitly structuring NER instructions. We also verify that combining the proposed code-based prompting method with the chain-of-thought prompting further improves performance.

cs.CL↗

arXiv2026

From Formal Language Theory to Statistical Learning: Finite Observability of Subregular Languages

We prove that all standard subregular language classes are linearly separable when represented by their deciding predicates. This establishes finite observability and guarantees learnability with simple linear models. Synthetic experiments confirm perfect separability under noise-free conditions, while real-data experiments on English morphology show that learned features align with well-known linguistic constraints. These results demonstrate that the subregular hierarchy provides a rigorous and interpretable foundation for modeling natural language structure. Our code used in real-data experiments is available at https://github.com/UTokyo-HayashiLab/subregular.

cs.CL↗

arXiv2026

Towards Artwork Explanation in Large-scale Vision Language Models

Large-scale Vision-Language Models (LVLMs) output text from images and instructions, demonstrating capabilities in text generation and comprehension. However, it has not been clarified to what extent LVLMs possess the ability to understand the knowledge necessary for explaining images, the complex relationships between various pieces of knowledge, and how they integrate these understandings into their explanations. To address this issue, we propose a new task: the artwork explanation generation task, along with its evaluation dataset and metrics for quantitatively assessing the understanding and utilization of knowledge about artworks. This task is apt for image description based on the premise that LVLMs are expected to have pre-existing knowledge of artworks, which are often subjects of wide recognition and documented information. It consists of two parts: generating explanations from images and titles of artworks, and generating explanations using only images, thus evaluating the LVLMs' language-based and vision-based knowledge. Alongside, we release a training dataset for LVLMs to learn explanations that incorporate knowledge about artworks. Our findings indicate that LVLMs not only struggle with integrating language and visual information but also exhibit a more pronounced limitation in acquiring knowledge from images alone.

cs.CV↗

arXiv2026

Diagnosing Vision Language Models' Perception by Leveraging Human Methods for Color Vision Deficiencies

Large-scale Vision-Language Models (LVLMs) are being deployed in real-world settings that require visual inference. As capabilities improve, applications in navigation, education, and accessibility are becoming practical. These settings require accommodation of perceptual variation rather than assuming a uniform visual experience. Color perception illustrates this requirement: it is central to visual understanding yet varies across individuals due to Color Vision Deficiencies, an aspect largely ignored in multimodal AI. In this work, we examine whether LVLMs can account for variation in color perception using the Ishihara Test. We evaluate model behavior through generation, confidence, and internal representation, using Ishihara plates as controlled stimuli that expose perceptual differences. Although models possess factual knowledge about color vision deficiencies and can describe the test, they fail to reproduce the perceptual outcomes experienced by affected individuals and instead default to normative color perception. These results indicate that current systems lack mechanisms for representing alternative perceptual experiences, raising concerns for accessibility and inclusive deployment in multimodal settings.

cs.CV↗

arXiv2026

HalluCitation Matters: Revealing the Impact of Hallucinated References with 300 Hallucinated Papers in ACL Conferences

Recently, we have often observed hallucinated citations or references that do not correspond to any existing work in papers under review, preprints, or published papers. Such hallucinated citations pose a serious concern to scientific reliability. When they appear in accepted papers, they may also negatively affect the credibility of conferences. In this study, we refer to hallucinated citations as "HalluCitation" and systematically investigate their prevalence and impact. We analyze all papers published at ACL, NAACL, and EMNLP in 2024 and 2025, including main conference, Findings, and workshop papers. Our analysis reveals that nearly 300 papers contain at least one HalluCitation, most of which were published in 2025. Notably, half of these papers were identified at EMNLP 2025, the most recent conference, indicating that this issue is rapidly increasing. Moreover, more than 100 such papers were accepted as main conference and Findings papers at EMNLP 2025, affecting the credibility.

cs.CL↗

arXiv2025

Oogiri-Master: Benchmarking Humor Understanding via Oogiri

Humor is a salient testbed for human-like creative thinking in large language models (LLMs). We study humor using the Japanese creative response game Oogiri, in which participants produce witty responses to a given prompt, and ask the following research question: What makes such responses funny to humans? Previous work has offered only limited reliable means to answer this question. Existing datasets contain few candidate responses per prompt, expose popularity signals during ratings, and lack objective and comparable metrics for funniness. Thus, we introduce Oogiri-Master and Oogiri-Corpus, which are a benchmark and dataset designed to enable rigorous evaluation of humor understanding in LLMs. Each prompt is paired with approximately 100 diverse candidate responses, and funniness is rated independently by approximately 100 human judges without access to others' ratings, reducing popularity bias and enabling robust aggregation. Using Oogiri-Corpus, we conduct a quantitative analysis of the linguistic factors associated with funniness, such as text length, ambiguity, and incongruity resolution, and derive objective metrics for predicting human judgments. Subsequently, we benchmark a range of LLMs and human baselines in Oogiri-Master, demonstrating that state-of-the-art models approach human performance and that insight-augmented prompting improves the model performance. Our results provide a principled basis for evaluating and advancing humor understanding in LLMs.

cs.CL↗

arXiv2025

Accurate and Diverse Recommendations via Propensity-Weighted Linear Autoencoders

In real-world recommender systems, user-item interactions are Missing Not At Random (MNAR), as interactions with popular items are more frequently observed than those with less popular ones. Missing observations shift recommendations toward frequently interacted items, which reduces the diversity of the recommendation list. To alleviate this problem, Inverse Propensity Scoring (IPS) is widely used and commonly models propensities based on a power-law function of item interaction frequency. However, we found that such power-law-based correction overly penalizes popular items and harms their recommendation performance. We address this issue by redefining the propensity score to allow broader item recommendation without excessively penalizing popular items. The proposed score is formulated by applying a sigmoid function to the logarithm of the item observation frequency, maintaining the simplicity of power-law scoring while allowing for more flexible adjustment. Furthermore, we incorporate the redefined propensity score into a linear autoencoder model, which tends to favor popular items, and evaluate its effectiveness. Experimental results revealed that our method substantially improves the diversity of items in the recommendation list without sacrificing recommendation accuracy.

cs.IR↗

arXiv2025

Agreement-Constrained Probabilistic Minimum Bayes Risk Decoding

Minimum Bayes risk (MBR) decoding generates high-quality translations by maximizing the expected utility of output candidates, but it evaluates all pairwise scores over the candidate set; hence, it takes quadratic time with respect to the number of candidates. To reduce the number of utility function calls, probabilistic MBR (PMBR) decoding partially evaluates quality scores using sampled pairs of candidates and completes the missing scores with a matrix completion algorithm. Nevertheless, it degrades the translation quality as the number of utility function calls is reduced. Therefore, to improve the trade-off between quality and cost, we propose agreement-constrained PMBR (AC-PMBR) decoding, which leverages a knowledge distilled model to guide the completion of the score matrix. Our AC-PMBR decoding improved approximation errors of matrix completion by up to 3 times and achieved higher translation quality compared with PMBR decoding at a comparable computational cost on the WMT'23 En$\leftrightarrow$De translation tasks.

cs.CL↗

arXiv2025

Toward Automatic Safe Driving Instruction: A Large-Scale Vision Language Model Approach

Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous driving. For example, LVLMs can generate safety-oriented descriptions of videos captured by road-facing cameras. However, ensuring comprehensive safety requires monitoring driver-facing views as well to detect risky events, such as the use of mobiles while driving. Thus, the ability to process synchronized inputs is necessary from both driver-facing and road-facing cameras. In this study, we develop models and investigate the capabilities of LVLMs by constructing a dataset and evaluating their performance on this dataset. Our experimental results demonstrate that while pre-trained LVLMs have limited effectiveness, fine-tuned LVLMs can generate accurate and safety-aware driving instructions. Nonetheless, several challenges remain, particularly in detecting subtle or complex events in the video. Our findings and error analysis provide valuable insights that can contribute to the improvement of LVLM-based systems in this domain.

cs.CV↗

arXiv2025

VLURes: Benchmarking VLM Visual and Linguistic Understanding in Low-Resource Languages

Vision Language Models (VLMs) are pivotal for advancing perception in intelligent agents. Yet, evaluation of VLMs remains limited to predominantly English-centric benchmarks in which the image-text pairs comprise short texts. To evaluate VLM fine-grained abilities, in four languages under long-text settings, we introduce a novel multilingual benchmark VLURes featuring eight vision-and-language tasks, and a pioneering unrelatedness task, to probe the fine-grained Visual and Linguistic Understanding capabilities of VLMs across English, Japanese, and low-resource languages, Swahili, and Urdu. Our datasets, curated from web resources in the target language, encompass ten diverse image categories and rich textual context, introducing valuable vision-language resources for Swahili and Urdu. By prompting VLMs to generate responses and rationales, evaluated automatically and by native speakers, we uncover performance disparities across languages and tasks critical to intelligent agents, such as object recognition, scene understanding, and relationship understanding. We conducted evaluations of ten VLMs with VLURes. The best performing model, GPT-4o, achieves an overall accuracy of 90.8% and lags human performance by 6.7%, though the gap is larger for open-source models. The gap highlights VLURes' critical role in developing intelligent agents to tackle multi-modal visual reasoning.

cs.CL↗

arXiv2025

J-ORA: A Framework and Multimodal Dataset for Japanese Object Identification, Reference, Action Prediction in Robot Perception

We introduce J-ORA, a novel multimodal dataset that bridges the gap in robot perception by providing detailed object attribute annotations within Japanese human-robot dialogue scenarios. J-ORA is designed to support three critical perception tasks, object identification, reference resolution, and next-action prediction, by leveraging a comprehensive template of attributes (e.g., category, color, shape, size, material, and spatial relations). Extensive evaluations with both proprietary and open-source Vision Language Models (VLMs) reveal that incorporating detailed object attributes substantially improves multimodal perception performance compared to without object attributes. Despite the improvement, we find that there still exists a gap between proprietary and open-source VLMs. In addition, our analysis of object affordances demonstrates varying abilities in understanding object functionality and contextual relationships across different VLMs. These findings underscore the importance of rich, context-sensitive attribute annotations in advancing robot perception in dynamic environments. See project page at https://jatuhurrra.github.io/J-ORA/.

cs.RO↗

arXiv2025

Decoding Uncertainty: The Impact of Decoding Strategies for Uncertainty Estimation in Large Language Models

Decoding strategies manipulate the probability distribution underlying the output of a language model and can therefore affect both generation quality and its uncertainty. In this study, we investigate the impact of decoding strategies on uncertainty estimation in Large Language Models (LLMs). Our experiments show that Contrastive Search, which mitigates repetition, yields better uncertainty estimates on average across a range of preference-aligned LLMs. In contrast, the benefits of these strategies sometimes diverge when the model is only post-trained with supervised fine-tuning, i.e. without explicit alignment.

cs.CL↗

arXiv2025

SinhalaMMLU: A Comprehensive Benchmark for Evaluating Multitask Language Understanding in Sinhala

Large Language Models (LLMs) demonstrate impressive general knowledge and reasoning abilities, yet their evaluation has predominantly focused on global or anglocentric subjects, often neglecting low-resource languages and culturally specific content. While recent multilingual benchmarks attempt to bridge this gap, many rely on automatic translation, which can introduce errors and misrepresent the original cultural context. To address this, we introduce SinhalaMMLU, the first multiple-choice question answering benchmark designed specifically for Sinhala, a low-resource language. The dataset includes over 7,000 questions spanning secondary to collegiate education levels, aligned with the Sri Lankan national curriculum, and covers six domains and 30 subjects, encompassing both general academic topics and culturally grounded knowledge. We evaluate 26 LLMs on SinhalaMMLU and observe that, while Claude 3.5 sonnet and GPT-4o achieve the highest average accuracies at 67% and 62% respectively, overall model performance remains limited. In particular, models struggle in culturally rich domains such as the Humanities, revealing substantial room for improvement in adapting LLMs to low-resource and culturally specific contexts.

cs.CL↗

arXiv2025

MMCIG: Multimodal Cover Image Generation for Text-only Documents and Its Dataset Construction via Pseudo-labeling

In this study, we introduce a novel cover image generation task that produces both a concise summary and a visually corresponding image from a given text-only document. Because no existing datasets are available for this task, we propose a multimodal pseudo-labeling method to construct high-quality datasets at low cost. We first collect documents that contain multiple images with their captions, and their summaries by excluding factually inconsistent instances. Our approach selects one image from the multiple images accompanying the documents. Using the gold summary, we independently rank both the images and their captions. Then, we annotate a pseudo-label for an image when both the image and its corresponding caption are ranked first in their respective rankings. Finally, we remove documents that contain direct image references within texts. Experimental results demonstrate that the proposed multimodal pseudo-labeling method constructs more precise datasets and generates higher quality images than text- and image-only pseudo-labeling methods, which consider captions and images separately. We release our code at: https://github.com/HyeyeeonKim/MMCIG

cs.CV↗

arXiv2025

Length Representations in Large Language Models

Large language models (LLMs) have shown remarkable capabilities across various tasks, that are learned from massive amounts of text-based data. Although LLMs can control output sequence length, particularly in instruction-based settings, the internal mechanisms behind this control have been unexplored yet. In this study, we provide empirical evidence on how output sequence length information is encoded within the internal representations in LLMs. In particular, our findings show that multi-head attention mechanisms are critical in determining output sequence length, which can be adjusted in a disentangled manner. By scaling specific hidden units within the model, we can control the output sequence length without losing the informativeness of the generated text, thereby indicating that length information is partially disentangled from semantic information. Moreover, some hidden units become increasingly active as prompts become more length-specific, thus reflecting the model's internal awareness of this attribute. Our findings suggest that LLMs have learned robust and adaptable internal mechanisms for controlling output length without any external control.

cs.CL↗