arXiv subjects

Junhong Liang

Publications and source records attributed to Junhong Liang.

11 recordsLinked to original sources

arXiv2026

MedRoundsQA: A Persona and Difficulty Aware Evaluation for Multi-Turn Medical Consultations

Medical benchmarks are dominated by single-turn, multiple-choice clinical cases that poorly reflect real consultations. Practically, clinicians elicit evidence interactively and patient communication varies widely. We introduce MedRoundsQA, a multi-turn diagnostic benchmark derived from 1,387 board-exam cases across 17 specialties. Each case is converted into a structured 24-slot clinical record, and then instantiated as controlled doctor-patient dual-agent dialogues under varying patient personas, with the underlying clinical content held fixed. We further classify cases by difficulty using model-based uncertainty to enable easy-to-hard analysis. Evaluations of fifteen LLM doctor agents show that (i) moving from a single-turn diagnosis on the standardized records to multi-turn consultations causes large degradations of roughly 13-39 points; (ii) more turns reliably improves question relevance, but diagnostic accuracy exhibits diminishing returns and typically plateaus after 6-12 turns; and (iii) patient persona differences can shift diagnosis accuracy by about 7-8 points (lowest to highest education), highlighting equity risks that single-turn benchmarks miss.

cs.AI↗

arXiv2026

ComplexityMT: Benchmarking the Interaction Between Text Complexity and Machine Translation

When a text is translated, does the translation retain the complexity of the original? We introduce ComplexityMT, a new challenge for assessing how text complexity and machine translation interact with and influence each other, using the Common European Framework of Reference for Languages (CEFR) levels as the measure of text complexity. Across six languages, including Arabic, Dutch, English, French, Hindi, and Russian, we evaluate three open-weight models, one closed model, and a commercial machine translation system on two tasks: i) correlation of CEFR with translation difficulty, and ii) shifts in CEFR levels of the source texts. Our experiments show that higher CEFR levels make texts more difficult to translate and that machine translation lowers the target text's CEFR level for most languages at the document level. These findings provide new insights for researchers and practitioners working on multilingual pedagogical content generation and MT difficulty estimation.

cs.CL↗

arXiv2026

When Similar Means Different: Evaluating LLMs on Arabic--Hebrew Cognates

Arabic and Hebrew, as closely related Semitic languages, share many words with similar surface forms, including true cognates, false friends, and modern loanwords. These lexical relationships create ambiguity for cross-lingual semantic interpretation, as similar forms may correspond to shared, divergent, or borrowed meanings. To evaluate whether LLMs can make these distinctions, we introduce SemCog Bench, a curated benchmark of 1,858 Arabic--Hebrew word pairs with sentence-level annotations for cognate identification and semantic disambiguation. We evaluate a diverse set of open-source and proprietary LLMs across multiple input representations and contextual settings. Our results show reliance on surface-form similarity, with weaker performance on false friends and wide variation on loanwords. We further find that context and scale yield model-dependent gains, while original-script inputs generally perform best. Our findings reveal limitations in cross-lingual form-meaning reasoning and establish SemCog Bench as a benchmark for cross-lingual lexical semantics. Our code and data are publicly available.

cs.CL↗

arXiv2026

ReViCo: Unveiling the Limitations of VLMs in Visual Text Understanding via Error Correction

Vision Language Models (VLMs) have shown great success in general visual tasks, yet they still struggle to deeply understand text within images. In this paper, we introduce ReViCo (Real Visual Correction), a benchmark designed to evaluate VLM text understanding through a novel task of visual text error correction. ReViCo challenges models to identify and fix text errors in real-world images, which requires a profound understanding of the interplay between visual text and its surrounding visual context. We benchmark various VLMs using two distinct paradigms: prompt-based strategy and targeted model training, both aimed at pushing the limits of current models. Our experiments reveal a striking performance gap between even the best VLMs and human, and further analysis also shows that most models struggle to accurately perceive the visual text, resulting in frequent correction errors. By highlighting these gaps, ReViCo provides a new benchmark foundation for developing more robust and text-aware VLMs.

cs.CV↗

arXiv2026

An Analysis of Language Frequency and Error Correction for Esperanto

Current Grammar Error Correction (GEC) initiatives tend to focus on major languages, with less attention given to low-resource languages like Esperanto. In this article, we begin to bridge this gap by first conducting a comprehensive frequency analysis using the Eo-GP dataset, created explicitly for this purpose. We then introduce the Eo-GEC dataset, derived from authentic user cases and annotated with fine-grained linguistic details for error identification. Leveraging GPT-3.5 and GPT-4, our experiments show that GPT-4 outperforms GPT-3.5 in both automated and human evaluations, highlighting its efficacy in addressing Esperanto's grammatical peculiarities and illustrating the potential of advanced language models to enhance GEC strategies for less commonly studied languages.

cs.CL↗

arXiv2026

PERL: Pinyin Enhanced Rephrasing Language Model for Chinese ASR N-best Error Correction

Chinese ASR correction is challenging because errors are often \emph{phonetic} (many characters share similar Pinyin) while the correction model must also obey a \emph{length constraint} under noisy N-best hypotheses. Existing approaches either exploit Pinyin only at the prompt/feature level without integrating it into model representations or rely on generative decoding that can drift in length. We propose \textbf{PERL}, a \textbf{constrained rephrasing pipeline} for Chinese N-best ASR correction that (i) predicts the target length and enforces it via mask budgeting, and (ii) fuses \emph{semantic} and \emph{phonetic} (Pinyin) representations through token-wise gates conditioned on sentence semantics. Experiments on Aishell-1 and our new domain N-best benchmark \textbf{DoAD} show that PERL consistently reduces CER (29.11\% on Aishell-1 and up to $\sim$70\% on DoAD) while maintaining low latency. We also provide analyzes of length generalization and phonetic--semantic interactions, showing when PERL relies on phonetic cues versus semantic constraints.

cs.CL↗

arXiv2026

ServImage: An Image Generation and Editing Benchmark from Real-world Commercial Imaging Services

Recent image generation and editing models demonstrate robust adherence to instructions and high visual quality on academic benchmarks. However, their performance on paid, real-world design projects remains uncertain. We introduce \textbf{ServImage}, a benchmark that explicitly correlates model outputs with economic value in commercial design projects. ServImage consists of (i) \textbf{\textit{ServImageBench}}: a dataset of 1.07k paid commercial design tasks and 2.05k designer deliverables totaling over \$295k, covering portrait, product, and digital content, along with 33k candidate images and 33k human annotations. (ii) \textbf{\textit{ServImageScore}}: an integrated scoring system that combines three quality dimensions: baseline requirements fulfilment, visual execution quality, and commercial necessity satisfaction. These three dimensions are designed to characterize the factors that drive human payment decisions and indicate whether an image is commercially acceptable. (iii) \textbf{\textit{ServImageModel}}: under this scoring system, we propose a payment prediction model trained on the human-annotated candidate images, achieving 82.00\% accuracy in predicting human payment decisions and producing calibrated payment probabilities. ServImage provides a comprehensive foundation for assessing the commercial viability of image generation models and offers a scalable resource for future research on economically grounded vision systems \href{https://github.com/FengxianJi/ServImage}{Github.}

cs.CV↗

arXiv2026

Cultural Benchmarking of LLMs in Standard and Dialectal Arabic Dialogues

There is a significant gap in evaluating cultural reasoning in LLMs using conversational datasets that capture culturally rich and dialectal contexts. Most Arabic benchmarks focus on short text snippets in Modern Standard Arabic (MSA), overlooking the cultural nuances that naturally arise in dialogues. To address this gap, we introduce ArabCulture-Dialogue, a culturally grounded conversational dataset covering 13 Arabic-speaking countries, in both MSA and each country's respective dialect, spanning 12 daily-life topics and 54 fine-grained subtopics. We utilize the dataset to form three benchmarking tasks: (i) multiple-choice cultural reasoning, (ii) machine translation between MSA and dialects, and (iii) dialect-steering generation. Our experiments indicate that the performance gap between MSA and Arabic dialects still exists, whereby the models perform worse on all three tasks in the dialectal setup, compared to the MSA one.

cs.CL↗

arXiv2026

Listen, Correct, and Feed Back: Spoken Pedagogical Feedback Generation

Grammatical error correction (GEC) and explanation (GEE) have made rapid progress, but real teaching scenarios also require \emph{learner-friendly pedagogical feedback} that is actionable, level-appropriate, and encouraging. We introduce \textbf{SPFG} (\textbf{S}poken \textbf{P}edagogical \textbf{F}eedback \textbf{G}eneration), a dataset built based on the Speak \& Improve Challenge 2025 corpus, pairing fluency-oriented transcriptions with GEC targets and \emph{human-verified} teacher-style feedback, including preferred/rejected feedback pairs for preference learning. We study a transcript-based Spoken Grammatical Error Correction (SGEC) setting and evaluate three instruction-tuned LLMs (Qwen2.5, Llama-3.1, and GLM-4), comparing supervised fine-tuning (SFT) with preference-based alignment (using DPO and KTO) for jointly generating corrections and feedback. Results show that SFT provides the most consistent improvements, while DPO/KTO yield smaller or mixed gains, and that correction quality and feedback quality are weakly coupled. Our implementation is available at https://github.com/Skywalker-Harrison/spfg.

cs.CL↗

arXiv2025

Vision Language Models Are Not (Yet) Spelling Correctors

Spelling correction from visual input poses unique challenges for vision language models (VLMs), as it requires not only detecting but also correcting textual errors directly within images. We present ReViCo (Real Visual Correction), the first benchmark that systematically evaluates VLMs on real-world visual spelling correction across Chinese and English. ReViCo contains naturally occurring errors collected from real-world image data and supports fine-grained evaluation at both image and token levels. Through comprehensive experiments on representative cascaded (Qwen) and native (InternVL) open-source models, as well as closed-source systems (GPT-4o, Claude), we show that current VLMs fall significantly short of human performance, particularly in correction. To address these limitations, we explore two solution paradigms: a Joint OCR-Correction pipeline and a Background Information enhanced approach, both of which yield consistent performance gains. Our analysis highlights fundamental limitations of existing architectures and provides actionable insights for advancing multimodal spelling correction.

cs.CL↗

arXiv2025

RAIR: Retrieval-Augmented Iterative Refinement for Chinese Spelling Correction

Chinese Spelling Correction (CSC) aims to detect and correct erroneous tokens in sentences. Traditional CSC focuses on equal length correction and uses pretrained language models (PLMs). While Large Language Models (LLMs) have shown remarkable success in identifying and rectifying potential errors, they often struggle with adapting to domain-specific corrections, especially when encountering terminologies in specialized domains. To address domain adaptation, we propose a \textbf{R}etrieval-\textbf{A}ugmented \textbf{I}terative \textbf{R}efinement (RAIR) framework. Our approach constructs a retrieval corpus adaptively from domain-specific training data and dictionaries, employing a fine-tuned retriever to ensure that the retriever catches the error correction pattern. We also extend equal-length into variable-length correction scenarios. Extensive experiments demonstrate that our framework outperforms current approaches in domain spelling correction and significantly improves the performance of LLMs in variable-length scenarios.

cs.CL↗