Computation and Language
Can Vision Language Models Be Adaptive in Mathematics Education? A Learner Model-based Rubric Study
Jie Gao, Yongan Yu, Junzhu Su et al. (+3 more)
Adaptive learning refers to educational technologies that track learners' learning progress and adapt the instructional process based on individual learners' learning performance. It is increasingly recognized as critical for developing an effective learning support tool.
Vision language models (VLMs) have seen adoption in mathematics education, and students have been using them as learning aids for personalized instruction. However, it is unknown whether VLMs have the ability to adapt to different learner profiles when providing mathematical instructions. Current VLMs lack a systematic evaluation framework for this adaptivity to different learner profiles in mathematics tutoring tasks. To address this gap, we draw on the learner model from the adaptive learning framework (Shute and Towle, 2018) and propose a learner model-based rubric. Our rubric formalizes adaptivity assessment into three aspects: cognitive aspects, motivational aspects, and complexity. We also evaluate two additional dimensions of VLM responses: correctness (of answers and solutions) and quality (of the response itself). Our experimental results show measurable differences in adaptivity across models and also reveal that current VLMs struggle to consistently produce learner model-based instructional responses, especially when receiving limited learner information.
Read the full abstract ▾
All authors Jie Gao, Yongan Yu, Junzhu Su, Yiran Lin, Adam K. Dube, Jackie Chi Kit Cheung
Computation and Language
Defining Cultural Capabilities for AI Evaluation: A Taxonomy Grounded in Intercultural Communication Theory
Isar Nejadgholi, Masoud Kianpour, Krishnapriya Vishnubhotla et al. (+1 more)
Tremendous efforts have been put into evaluating the inclusivity and effectiveness of AI systems across cultures. However, the cultural capabilities considered in much of the literature remain vaguely defined, are referred to using interchangeable terminology, and are typically limited to recalling accurate information about various demographics, regions, and nationalities. To address this construct ambiguity, we draw from Intercultural Communication scholarship and propose a three-level taxonomy of AI-relevant cultural capabilities: Cultural Awareness answers "Does the model know?", Cultural Sensitivity answers "How does it frame its knowledge?", and Cultural Competence answers "Can it adapt as the interaction evolves?". Beyond conceptual clarification, we position this taxonomy as a practical tool for improving the validity and interpretability of AI evaluation in real-world, multicultural settings. Without such construct clarity, evaluation results risk overstating model capabilities and may lead to inappropriate deployment decisions in culturally sensitive contexts.
Read the full abstract ▾
All authors Isar Nejadgholi, Masoud Kianpour, Krishnapriya Vishnubhotla, Maryam Molamohamadi
Computation and Language
Ontology for Policing: Conceptual Knowledge Learning for Semantic Understanding and Reasoning in Law Enforcement Reports
Anita Srbinovska, Jansen Orfan, Adrian Martin et al. (+1 more)
Law enforcement reports contain structured fields and written narratives. However, many incident facts that are needed for review, police training, and investigations are in natural
language and require manual reading. We propose a framework using symbolic methods for converting narratives into evidence-linked facts. Our objective is to measure the value of narratives to recover incident details only from the unstructured text and build temporal graphs with time cues and domain axioms. We achieve this by redacting personal identifiers, semantic parsing, predicate mapping to ontology, and
reasoning. We evaluate the symbolic approach on 450 property crime reports and a short human review. Of the extracted events from the system, 54.1% had a confidence score of at least 0.80 and 93.7% were mapped through the PropBank–VerbNet–WordNet semantic path. 100% agreement was reached on incident initiation, stolen items, and temporal cues and lower agreement for forced entry interpretation.
Read the full abstract ▾
All authors Anita Srbinovska, Jansen Orfan, Adrian Martin, Ernest Fokoué
Computation and Language
Reference-Free Reinforcement Learning Fine-Tuning for MT: A Seq2Seq Perspective
Ernesto Garcia-Estrada, Carlos Escolano and José A. R. Fonallosa
Production machine translation relies overwhelmingly on encoder-decoder Seq2Seq models, yet reinforcement learning approaches to MT fine-tuning have largely targeted decoder-only LLMs at $\geq$7B parameters, with limited systematic study of encoder-decoder architectures. We apply Group Relative Policy Optimization to NLLB-200 (600M and 1.3B) using a hybrid reference-free reward (LaBSE and COMET-Kiwi) that requires no parallel data at fine-tuning time, evaluating across 13 typologically diverse
languages. GRPO yields consistent improvements on all 13
languages, up to $+$5.03 chrF++ for Traditional Chinese, and, without any target-
language data, competes with 3-epoch supervised fine-tuning on morphologically complex
languages . We identify a consistent empirical pattern in which gains are largest where baseline performance is weakest and reward discriminability is highest, making this approach most effective precisely where parallel data is scarcest, and replicate this pattern across English and Spanish source
languages.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.HC
SLIP & ETHICS: Graduated Intervention for AI Emotional Companions
Minseo Kim
AI emotional companions face a safety-rapport paradox: restrictive safeguards can damage supportive alliance, while permissive systems risk user harm. We present SLIP (Staged Layers of Intervention Protocol), a four-stage graduated methodology deriving interventions (none, soft, hard) from structured qualitative indicators – affect intensity (a) and narrative dynamism (m) – alongside ETHICS (Emergent Taxonomy for Human-AI Interaction Context Signals), a "signals not labels" taxonomy. An evaluation combining a small-scale production deployment (N=68 entries, 10 users, 10 weeks) with a synthetic persona battery (N=91, 5 behavioral-risk profiles) achieved 0% false positives for the flow persona and showed expected escalation patterns in crisis-oriented personas. However, initial results showed that 8 consecutive days of high-energy elevation produced zero interventions (0/8), exposing a boundary where the "do not pathologize" principle conflicts with safety. A subsequent three-model stress test demonstrated that increased model capability improves detection from 0/8 to 6/8 while preserving 0/10 flow false positives in the largest model. Read as preliminary, these findings position graduated intervention as a design direction for navigating – not resolving – the safety-rapport tension in affective computing.
Read the full abstract ▾
Computation and Language
Shuaiyi Li, Zhisong Zhang, Yan Wang et al. (+5 more)
Block
attention, which processes the input as separate blocks that cannot attend to one another, offers significant potential to improve KV cache reuse in long-context scenarios such as
Retrieval-Augmented Generation (RAG). However, its broader application is hindered by two key challenges: the difficulty of segmenting input text into meaningful, self-contained blocks, and the inefficiency of existing block fine-tuning methods that risk degrading performance. To address these, we first construct SemanticSeg, a large and diverse semantic
segmentation dataset containing over 30k instances across 16 categories-including books, code, web text, and conversations with text lengths ranging from 2k to 32k. Using this
dataset, we train a lightweight segmenter to automatically partition text into human-instinct-aligned blocks with controllable granularity. Second, we propose block
distillation, a training framework that is more efficient than block fine-tuning, which uses a frozen full-
attention teacher model to guide the block-
attention student. This framework integrates three novel components: block sink
tokens to mitigate information loss at block boundaries, block dropout to leverage training signals from all blocks, and
token-level loss weighting to focus learning on block-
attention-sensitive
tokens. Experiments across multiple models and
benchmarks demonstrate that our segmenter outperforms heuristic and statistical baselines, and block
distillation achieves near-full-
attention performance under block
attention, establishing a practical and scalable pathway for deploying block
attention.
Read the full abstract ▾
All authors Shuaiyi Li, Zhisong Zhang, Yan Wang, Lei Zhu, Dongyang Ma, Chenlong Deng, Yang Deng, Wai Lam
Computation and Language
Linked Multi-Modal Data on Russian Domestic and Foreign Policy Speeches
Daria Blinova, Gayathri Emuru, Rakesh Emuru et al. (+4 more)
This paper introduces a
dataset of interlinked
multimodal political communications from the Russian government, addressing persistent deficiencies in the availability of social text- and image-based data for authoritarian politics contexts. The
dataset comprises two large corpora of official
speeches delivered by senior actors within the Kremlin and the Russian Ministry of Foreign Affairs over multiple decades. For each
speech, we provide Russian- and English-
language texts, associated images and captions where available, and harmonized metadata including (e.g.) dates, speakers, (geo)locations, and official government content tags. Unique identifiers link images to
speeches and align Russian and English versions of the same communication texts. We further augment these linked
datasets with validated topical annotations for both
speech texts and
speech images, which are generated via
transformer-based
multimodal topic modeling and refined by a Russian politics expert. The resulting data resources support
multimodal,
multilingual, temporal, and/or spatial analyses of (authoritarian) political communication and offer a valuable testbed for social science research and large
language model (LLM) applications in political domains.
Read the full abstract ▾
All authors Daria Blinova, Gayathri Emuru, Rakesh Emuru, Kushagradheer Shridheer Srivastava, Mina Rulis, Sunita Chandrasekaran, Benjamin E. Bagozzi
Computation and Language · Cross-listed from cs.CV
Are VLMs Seeing or Just Saying? Uncovering the Illusion of Visual Re-examination
Chufan Shi, Cheng Yang, Yaokang Wu et al. (+4 more)
Vision-
Language Models (VLMs) often produce self-reflective statements like "let me check the figure again" during
reasoning. Do such statements trigger genuine visual re-examination, or are they merely learned textual patterns? We investigate this via VisualSwap, an image-swap probing framework: after a model reasons over an image, we replace it with a visually similar but semantically different one and test whether the model notices. We introduce VS-Bench, 800 image pairs curated from MathVista, MathVerse, MathVision, and MMMU-Pro. Experiments on Qwen3-VL, Kimi-VL, and ERNIE-VL reveal a striking failure: models overwhelmingly miss the swap, with accuracy dropping by up to 60%. Counterintuitively, thinking models are nearly 3x more vulnerable than their instructed counterparts, and scaling offers no mitigation. Multi-turn user instructions restore visual grounding, but self-generated reflective statements during continuous generation do not.
Attention analysis explains why: user instructions substantially elevate
attention to visual
tokens, whereas self-reflection does not. Current VLMs tend to say rather than actually see when claiming to perform visual re-examination. Our code and
dataset are available at the project page: https://visualswap.github.io
Read the full abstract ▾
All authors Chufan Shi, Cheng Yang, Yaokang Wu, Linghao Jin, Bo Shui, Taylor Berg-Kirkpatrick, Xuezhe Ma
Computation and Language · Cross-listed from cs.HC
Conversations in Space: Non-Linear LLM Interaction in Everyday Use
Rifat Mehreen Amin, Alperen Adatepe, Daniela Fernandes et al. (+2 more)
As LLM conversations grow, their histories capture alternative directions, decisions, and evolving lines of thought that can be difficult to navigate through chat alone. We investigate an interaction concept that represents the same conversation through two synchronized views: a familiar linear chat for ongoing dialogue and a spatial canvas for navigating its emerging structure. To investigate this interaction concept, we developed CanvasConvo, which allows conversations to branch into alternative paths that remain accessible across both views. In a five-day field deployment with 24 participants, we examined how people appropriated this parallel representation in self-directed knowledge work. Participants selectively moved between the two views rather than replacing chat with the canvas. Chat remained central to conversational interaction, while the canvas supported overview, revisitation, and exploration of alternatives. Adoption was uneven, revealing challenges around established chat habits, transitions between representations, and understanding branch context. Our findings inform the design of user interfaces for LLMs that combine linear and non-linear conversation representations.
Read the full abstract ▾
All authors Rifat Mehreen Amin, Alperen Adatepe, Daniela Fernandes, Daniel Buschek, Andreas Butz
Computation and Language · Cross-listed from cs.SE
BootstrapAgent: Distilling Repository Setup into Reusable Agent Knowledge
Sihan Fu, Oucheng Liu, Shiyuan Wang et al. (+2 more)
Code
agents increasingly help developers work with unfamiliar repositories, but every such task depends on a costly prerequisite: bootstrapping the repository into a usable development state. This process requires substantial trial-and-error exploration, yet the resulting knowledge–resolved dependencies, repair strategies–stays trapped in a single conversation, unavailable to future
agents. We therefore formulate repository bootstrapping as a reusable startup knowledge problem and introduce BootstrapAgent, a multi-
agent framework that distills the heuristics discovered during bootstrap exploration into a persistent, verifiable,
agent-consumable .bootstrap contract. Through evidence extraction, structured planning, deterministic Docker-based verification, and trace-driven repair, BootstrapAgent generates a contract covering environment setup, diagnostic checks, minimal verification, and accumulated repair knowledge. We further propose warm repair with clean replay to accelerate iterative debugging without sacrificing cold-start reproducibility, and a delta repair with sanity check to prevent reward hacking. Experiments on three
benchmarks show that BootstrapAgent achieves a 92.9% success rate, outperforming the baseline by over 10% while reducing downstream
agent token usage by 25.9% and build time by 22.3%. Our code is available at https://github.com/Vossera/BootstrapAgent.
Read the full abstract ▾
All authors Sihan Fu, Oucheng Liu, Shiyuan Wang, Jin Shi, Chengkun Wei
Computation and Language
ForMaT: Dataset for Visually-Grounded Multilingual PDF Translation
Michał Ciesiółka, Dawid Wiśniewski, Adrian Charkiewicz et al. (+1 more)
We present ForMaT (Format-Preserving
Multilingual Translation), a parallel corpus of 3,956 PDFs across 15
language pairs that preserves original layout metadata proposed for
multimodal machine translation. To ensure structural diversity in the
dataset, we employ K-Medoids sampling over 45
geometric features, capturing complex elements like nested tables and formulas to focus only on visually diverse PDF documents. Our evaluation reveals that current MT systems struggle with spatial grounding and
geometric synchronization, often losing the link between text and its visual context. ForMaT provides a
benchmark for developing layout-aware translation models that integrate visual and textual context for high-fidelity document reconstruction.
Read the full abstract ▾
All authors Michał Ciesiółka, Dawid Wiśniewski, Adrian Charkiewicz, Kamil Guttmann
Computation and Language
CompactQE: Interpretable Translation Quality Estimation via Small Open-Weight LLMs
Kamil Guttmann, Zofia Fraś, Artur Nowakowski et al. (+1 more)
Current state-of-the-art Quality Estimation (QE) in machine translation relies on massive, proprietary LLMs, raising data
privacy concerns. We demonstrate that smaller, open-source LLMs (<30B parameters) are a viable, cost-effective and
privacy-preserving alternative. Using a single-pass prompting strategy, our models simultaneously generate quality scores, MQM error annotations, suggested error corrections, and full post-editions. Our analysis shows these models achieve highly competitive system-level correlations with human judgments that outperform traditional neural metrics, fine-tuned models, and human inter-annotator agreement, effectively approximating the capabilities of much larger proprietary LLMs.
Read the full abstract ▾
All authors Kamil Guttmann, Zofia Fraś, Artur Nowakowski, Krzysztof Jassem
Computation and Language
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
Wentao Qiu, Haotian Hu, Fanyi Wang et al. (+2 more)
Large
language model (LLM)
agents require long-term
memory to leverage information from past interactions. However, existing
memory systems often face a fidelity–efficiency trade-off: raw dialogue histories are expensive, while flat facts or summaries may discard the structure needed for precise recall. We propose DimMem, a lightweight dimensional
memory framework that represents each
memory as an atomic, typed, and self-contained unit with explicit fields such as time, location, reason, purpose, and keywords. This representation exposes the structure needed for dimension-aware
retrieval,
memory update, and selective assistant-context recall without storing full histories in the model context. Across LoCoMo-10 and LongMemEval-S, DimMem achieves 81.43% and 78.20% overall accuracy, respectively, outperforming existing lightweight
memory systems while reducing LoCoMo per-query
token cost by 24%. We further show that dimensional
memory extraction is learnable by compact models: after fine-tuning on the DimMem schema, a Qwen3-4B extractor surpasses LightMem with GPT-4.1-mini on both
benchmarks and reaches performance comparable to, or better than, much larger extractors in key settings. These results suggest that explicit dimensional structuring is an effective and efficient foundation for long-term
memory in LLM
agents. Code is available at https://github.com/ChowRunFa/DimMem.
Read the full abstract ▾
All authors Wentao Qiu, Haotian Hu, Fanyi Wang, Jinwei Kong, Yu Zhang
Computation and Language · Cross-listed from cs.AI
Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR
Chanuk Lee, Sangwoo Park, Minki Kang et al. (+1 more)
Reinforcement learning with verifiable rewards (RLVR) is a scalable paradigm for improving the mathematical
reasoning of large
language models, but it is fundamentally limited by exploration: the policy can only improve on trajectories it has already sampled. Sampling more rollouts alleviates this at prohibitive compute cost, while objective-level modifications offer little control over what is explored. We propose NudgeRL, a framework for structured, diversity-driven exploration in RLVR whose core component, Strategy Nudging, conditions each rollout on a lightweight strategy-level context, without requiring the context generator to solve the problem itself. To learn from such exploration, we decompose the advantage into inter- and intra-context terms and add a policy correction term that transfers discovered behaviors back to the base policy. Across five mathematical
reasoning benchmarks, NudgeRL with 8 rollouts matches the strongest GRPO baseline using 32 rollouts with roughly 5 times fewer total
tokens and 2.9 times less training compute. Our code is available at https://github.com/tally0818/NudgeRL.
Read the full abstract ▾
All authors Chanuk Lee, Sangwoo Park, Minki Kang, Sung Ju Hwang
Computation and Language
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
Jiachen Zhu, Zhuoying Ou, Congmin Zheng et al. (+9 more)
Large
Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a
dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce Neural Collaborative Context Engineering (NCCE), a framework that transitions optimization from a static global search to dynamic, instance-wise routing. NCCE first bootstraps a diverse catalog of anchor contexts and then employs a novel Context-CF Co-
Evolution mechanism. This stage establishes a synergistic feedback loop: a lightweight Neural Collaborative Filtering (NCF) model learns instance-context preferences to guide the generation of specialized context variants, while the newly evaluated contexts continuously refine the NCF model's understanding of latent preferences. At inference time, the trained NCF model acts as a context router, dynamically assigning the most suitable context strategy to each unseen instance. Theoretical Proofs and comprehensive experiments demonstrate that by matching individual inputs with their optimal contexts, NCCE significantly improves task accuracy, highlighting the critical importance of personalization in LLM context engineering.
Read the full abstract ▾
All authors Jiachen Zhu, Zhuoying Ou, Congmin Zheng, Yuxiang Chen, Zeyu Zheng, Rong Shan, Lingyu Yang, Lionel Z. Wang, Weiwen Liu, Yong Yu, Weinan Zhang, Jianghao Lin
Computation and Language
Huacan Chai, Yukai Wang, Yingxuan Yang et al. (+7 more)
Existing
benchmarks for
multimodal memory reasoning largely evaluate systems within pre-assembled contexts, but under-evaluate whether
agents can use evidence distributed across independently originated sources. We argue that source-distributed
memory composition is an important and under-examined bottleneck in
multimodal agent memory, especially when relevant evidence is fragmented across heterogeneous artifacts such as conversations, profiles, screenshots, tables, images, and documents. To address this gap, we introduce Source-distributed
Multimodal Memory Benchmark(SMMBench), which measures whether
agents can retrieve, align, and compose
multimodal evidence scattered across multiple sources rather than reason within a single curated context. SMMBench evaluates four core capabilities: (1) cross-source
multimodal reasoning; (2) conflict resolution; (3) preference
reasoning; (4)
memory-grounded action prediction. The
benchmark contains 1877 samples grounded in 264 sources. Experiments on representative
memory-style and
retrieval-based baselines show that current systems still struggle on these capabilities, positioning source-distributed
multimodal memory as an important and still under-evaluated challenge for
multimodal agents. Our data are available at https://huggingface.co/
datasets/HuacanChai/SMMBench.
Read the full abstract ▾
All authors Huacan Chai, Yukai Wang, Yingxuan Yang, Dan Peng, Yuanyi Song, Zhihui Fu, Weiwen Liu, Jianghao Lin, Jun Wang, Weinan Zhang
Computation and Language
H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structure
Jiawei Yu, Yixiang Fang, Xilin Liu et al. (+1 more)
Memory data are ubiquitous in Large
Language Model (LLM)-based
agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit
agents'
memory for improving their performance on the question-answering (QA) task, but they lack a principled mechanism for effectively modeling how
memory data evolves over time and retrieving
memory data effectively, leading to poor performance in
memory utilization. To fill this gap, we present H-Mem, a novel
memory mechanism via a hybrid structure that can not only effectively model the
evolution of
agent memory over a long period of time, but also provide an efficient
memory retrieval approach. Particularly, H-Mem builds a temporal and semantic tree structure that allows the short-term
memory data to evolve progressively into long-term
memory data, where the latter provides summarized information about the former, while simultaneously constructing a knowledge graph to capture the relationships between entities in
memory. Moreover, it offers an effective
memory retrieval approach by exploiting the hybrid structure of the tree and graph structures. Extensive experiments on three
agent memory benchmarks show that H-Mem achieves state-of-the-art performance on the QA task.
Read the full abstract ▾
All authors Jiawei Yu, Yixiang Fang, Xilin Liu, Yuchi Ma
Computation and Language
ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
Jiahui Guang, Haiyan Wang, Yingjie Zhu et al. (+4 more)
Multimodal large
language models (MLLMs) may memorize sensitive cross-modal information during pretraining, making machine unlearning (MU) crucial. Existing methods typically evaluate unlearning effectiveness based on output deviations, while overlooking the generation quality after unlearning. This can easily lead to hallucinated or rigid responses, thereby affecting the usability and safety of the unlearned model. To address this issue, we propose ASRU, a controllable
multimodal unlearning framework that incorporates generation quality as a core evaluation objective. ASRU first induces initial refusal behavior through activation redirection, and then optimizes fine-grained refusal boundaries using a customized reward function, thereby achieving a better trade-off between target knowledge unlearning and model utility. Experiments on Qwen3-VL show that ASRU significantly improves unlearning effectiveness (+24.6%) on average and generation quality (5.8X) on average while effectively preserving model utility, using only a small amount of retained supervision data.
Read the full abstract ▾
All authors Jiahui Guang, Haiyan Wang, Yingjie Zhu, Cuiyun Gao, Jing Li, Di Shao, Zhaoquan Gu
Computation and Language
Few-Shot Large Language Models for Actionable Triage Categorization of Online Patient Inquiries
Liqi Zhou and Jiafu Li
Online patient inquiries are often informal, incomplete, and written before professional assessment, yet they must still be routed to an appropriate level of clinical follow-up. We study this as a four-class actionable triage task – self-care, schedule-visit, urgent-clinician-review, or emergency-referral, and ask whether prompted large
language models (LLMs) can support such routing under low-resource labeling conditions. Using the public HealthCareMagic-100K corpus, we construct a 300-example human calibrated gold evaluation set, a 700-example auto-labeled silver training set, and a 40-example few-shot pool. We compare Term Frequency-Inverse Document Frequency (TF-IDF) and Bidirectional Encoder Representations from
Transformers for Biomedical Text Mining (BioBERT) baselines train on silver labels against six prompted LLMs under 0-shot, 4-shot, and 12-shot conditions respectively. Accordingly, we evaluate with macro-$F_1$ alongside safety-aware metrics, including emergency-recall, under-triage rate, and severe under-triage rate. The strongest LLM (Claude Haiku 4.5, 12-shot) reaches macro-$F_1$ 0.475, exceeding the best supervised baseline (BioBERT, 0.378) on point estimate, with overlapping confidence intervals. Few-shot prompting and two-model agreement help in label-dependent ways: self-care agreement is reliable, urgent-clinician-review is not. We conclude that LLMs can support triage prioritization and selective human review, but not autonomous deployment.
Read the full abstract ▾
Computation and Language
VCG-Bench: Towards A Unified Visual-Centric Benchmark for Structured Generation and Editing
Xiaoyan Su, Peijie Dong, Zhenheng Tang et al. (+8 more)
Despite the rapid advancements in
Vision-
Language Models (VLMs), a critical gap remains in their ability to handle structured, controllable diagrammatic tasks essential for professional workflows. Existing methods predominantly rely on pixel-based synthesis, which operates in probabilistic pixel spaces and is inherently limited in editability and fidelity. Instead, we propose a new Diagram-as-Code paradigm with symbolic logic that leverages mxGraph Extensible Markup
Language (XML) for precise diagram generation and editing. We present VCG-Bench, a unified
benchmark for visual-centric mxGraph tasks. VCG-Bench comprises: (1) a taxonomized
dataset of 1,449 diverse diagrams spanning 6 domains and 15 sub-domains, (2) a paradigm definition that integrates Generation (
Vision-to-Code) and Editability (Code-to-Code), (3) a Tailored Evaluation Protocol employing multi-dimensional metrics such as mxGraph Execution Success Rate, Style Consistency Score (SCS), etc. Experimental results highlight the challenges faced by current State-of-the-Art (SOTA) VLMs in structured fidelity and instruction compliance, reflecting their
vision and
reasoning capabilities.
Read the full abstract ▾
All authors Xiaoyan Su, Peijie Dong, Zhenheng Tang, Song Tang, Yuyao Zhai, Kaitao Lin, Liang Chen, Gai Yuhang, Yuyu Luo, Qiang Wang, Xiaowen Chu
Computation and Language
Yichen Zhu, Xiaoming Shi, Peng Zhao et al. (+3 more)
Block discrete
diffusion language models factorize a sequence autoregressively over fixed-size positional blocks, decoupling within-block parallel denoising from across-block conditioning. We argue that this rigid partition wastes structure already present in the sequence: blocks defined by position rather than by content separate semantically coherent
tokens and group unrelated ones together. We introduce the Dynamic Chunking
Diffusion Model (DCDM), which replaces positional blocks with content-defined semantic chunks. At its core is Chunking
Attention, a differentiable layer that routes
tokens into $K$ clusters parameterized by learnable subspaces and shaped end-to-end by the
diffusion objective. The resulting cluster assignments induce a chunk-causal
attention mask under which a discrete
diffusion denoiser factorizes the sequence likelihood autoregressively over semantic chunks, strictly generalizing block discrete
diffusion. On downstream
benchmarks at parameter scales up to 1.5B, DCDM consistently improves over both unstructured and positional-block
diffusion baselines, with the advantage stable across scales and visible early in training.
Read the full abstract ▾
All authors Yichen Zhu, Xiaoming Shi, Peng Zhao, Weiyu Chen, Debing Zhang, James Kwok
Computation and Language
Evaluating Chinese Ambiguity Understanding in Large Language Models
Junwen Mo, Yuanzhi Lu, Yifang Xue et al. (+2 more)
Linguistic ambiguity is critical to the robustness of Large
Language Models (LLMs), yet existing research focuses mostly on English, with limited
attention devoted to Chinese. Existing Chinese ambiguity
datasets (e.g., CHAmbi) suffer from poor scalability. Guided by Potential Ambiguity (PA) Theory, we design a semi-automatic pipeline to construct CHA-Gen. It is the first PA Theory-grounded Chinese ambiguity
dataset, which comprises 5,712 sentences (2,414 ambiguous, 3,298 unambiguous) across 18 potential ambiguous structures. Evaluating LLMs (e.g. Gemma 3, Qwen 2.5/3 series) via direct querying and machine translation, we find that LLMs struggle with ambiguity detection (improved by CoT prompting). Analysis of Qwen3-32B's CoT rationales reveals three common failure modes: ambiguity blindness, misattribution, and premature resolution. Uncertainty quantification with semantic
entropy metric shows higher uncertainty for ambiguous sentences. Moreover, instruction tuning induces overconfidence, whereas Base models better capture semantic diversity. We further observe that models exhibit a bias toward dominant interpretations. Our work provides a scalable approach for Chinese ambiguity corpus and insights into LLMs' ambiguity handling, laying a foundation for enhancing Chinese ambiguity research in LLMs.
Read the full abstract ▾
All authors Junwen Mo, Yuanzhi Lu, Yifang Xue, Ke Xu, Hideki Nakayama
Computation and Language
Toward LLMs Beyond English-Centric Development
Sho Takase and Ukyo Honda
Through an analysis of sequences generated by open-weight large
language models (LLMs), we demonstrate that LLMs are heavily biased toward English. While continual pre-training is commonly used to adapt LLMs to a target
language, we show that it does not offer a cost advantage over training from scratch, even for improving cultural understanding in the target
language. These findings suggest that dedicated per-
language investment may become increasingly important for future LLM development, rather than relying primarily on the expansion of English-centric resources.
Read the full abstract ▾
Computation and Language
PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding
Shengyin Sun, Yiming Li, Renxi Liu et al. (+7 more)
Diffusion large
language models (dLLMs) generate text by iteratively denoising masked
token sequences. Although dLLMs can predict all masked positions in parallel within each step, the large number of denoising iterations still makes inference expensive. This cost can be reduced spatially by unmasking multiple
tokens per step, or temporally by collapsing multiple denoising steps into one verification call. We propose Parallel Speculative Decoding (PSD), a training-free framework that jointly improves inference along both axes. Using the confidence scores from a single forward pass, PSD selects positions to unmask via a configurable, adaptive unmasking policy and constructs multi-depth speculative drafts without extra model calls. A final batched verification pass then applies hierarchical acceptance, keeping the deepest draft that remains consistent with the updated predictions. Experiments on three dLLMs across
reasoning and code generation tasks show that PSD achieves favorable trade-offs between inference efficiency and generation quality, reaching up to $5.5\times$
tokens per forward pass with accuracy comparable to greedy decoding.
Read the full abstract ▾
All authors Shengyin Sun, Yiming Li, Renxi Liu, Xinqi Li, Hui-Ling Zhen, Weizhe Lin, Chen Chen, Xianzhi Yu, Mingxuan Yuan, Chen Ma
Computation and Language
Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
Vinayshekhar Bannihatti Kumar, Disha Makhija, Manoj Ghuhan Arivazhagan et al. (+1 more)
Large
language models (LLMs) achieve high pass rates on code generation
benchmarks, yet whether they can transfer this ability to
languages absent from pretraining remains poorly understood. We introduce PyLang, a minimal imperative
language absent from all pretraining corpora, and evaluate frontier models zero-shot and fine-tuned Qwen3 (4B, 8B, 32B) on 352 problems. We find that fine-tuning quickly teaches syntax but fails to transfer semantic competence: Python outperforms PyLang by up to 19% across all configurations, and no intervention (multi-task learning, preference tuning, code infilling, or latent-space objectives) closes the gap. An LLM judge reveals that frontier models select an identical
algorithm to Python 80% of the time, yet cannot translate it into a working PyLang implementation., and CKA analysis confirms that fine-tuned models converge to nearly identical internal representations across
languages (CKA > 0.97) while diverging at the output stage. We term this the implementation fidelity gap: models possess
language-agnostic algorithmic understanding but cannot express it in an unfamiliar
language. Our findings highlight the need for training methods that decouple
reasoning from
language-specific realization.
Read the full abstract ▾
All authors Vinayshekhar Bannihatti Kumar, Disha Makhija, Manoj Ghuhan Arivazhagan, Rashmi Gangadharaiah
Computation and Language · Cross-listed from cs.LG
VSPO: Vector-Steered Policy Optimization for Behavioral Control
Xuechen Zhang, Zijian Huang, Kai Yang et al. (+3 more)
Modern
language models often need to optimize a primary accuracy objective while also accommodating secondary behavioral preferences, such as verbosity, agreeableness, or the level of technical expertise in its response. In practice, a base model may exhibit a desired behavior very rarely or not at all. Thus, endowing the model with a target behavior creates a sparse behavioral reward bottleneck. To address such multi-objective problems, we introduce Vector-Steered Policy Optimization (VSPO) which employs a steering vector associated with the target behavior to control the behavior intensity of the generated rollouts. VSPO is obtained by modifying GRPO to sample rollouts with varying steering intensities. This process can be interpreted as an on-policy latent self-
distillation procedure where the model internalizes its steering vector. By varying steering intensities, VSPO upsamples rare behaviors and enriches rollout diversity, which alleviates the sparse reward issue and provably accelerates the policy optimization. Through comprehensive theory and experiments, we establish that VSPO has favorable properties compared to vanilla reward shaping and other alternative approaches. Specifically, under a bandit abstraction, VSPO provably achieves better iteration complexity than reward-shaped GRPO when the steering-induced distributions are sufficiently aligned with the target behavior. We evaluate VSPO across multiple
reasoning benchmarks, including MATH and MMLU-Pro, for four target behaviors: explanation expertise, confidence expression, robustness to misleading context, and response verbosity. Our results show that VSPO consistently improves the control along target behavior while maintaining or improving task accuracy compared with reward shaping, teacher-trace
distillation, and guidance-based baselines.
Read the full abstract ▾
All authors Xuechen Zhang, Zijian Huang, Kai Yang, Weijia Zhang, Jiasi Chen, Samet Oymak
Computation and Language
MHGraphBench: Knowledge Graph-Grounded Benchmarking of Mental Health Knowledge in Large Language Models
Weixin Liu, Congning Ni, Shelagh A. Mulvaney et al. (+4 more)
Large
language models (LLMs) are increasingly used in the mental health domain, yet it remains unclear how well they capture related biomedical knowledge and how reliably they apply it to clinically salient structured judgments. Here, we present a knowledge-graph (KG)-grounded
benchmark for assessing LLMs on mental-health entity recognition, relation judgment, and two-hop
reasoning. The
benchmark is derived from PrimeKG and comprises nine task families with KG-supported answers and controlled negative options. Experiments across 15 closed- and open-source LLMs reveal a persistent recognition-to-judgment gap: leading models achieve near-ceiling performance on entity typing and on the small relation-typing subset, yet they still struggle with relation prediction and two-hop
reasoning. Additionally, short KG-derived snippets benefit some models but degrade performance for others. Moreover, output-format reliability can substantially influence measured performance under constrained multiple-choice settings, highlighting the critical role of response validity in
benchmark-based evaluation. MHGraphBench should therefore be interpreted as evaluating agreement with a curated mental-health slice of PrimeKG under a constrained multiple-choice interface, rather than as a direct assessment of real-world clinical safety.
Read the full abstract ▾
All authors Weixin Liu, Congning Ni, Shelagh A. Mulvaney, Susannah L. Rose, Murat Kantarcioglu, Bradley A. Malin, Zhijun Yin
Computation and Language
Calibrating LLMs with Semantic-level Reward
Fengfei Yu, Ruijia Niu, Dongxia Wu et al. (+2 more)
As large
language models (LLMs) are deployed in consequential settings such as medical question answering and legal
reasoning, the ability to estimate when their outputs are likely to be correct is essential for safe and reliable use, requiring well-calibrated uncertainty. Standard reinforcement learning with verifiable rewards (RLVR) trains models with a binary correctness reward that is indifferent to confidence, providing no penalty for confident but wrong predictions and thereby degrading calibration. Recent work addresses this by training models to produce verbalized confidence scores alongside answers and rewarding agreement with correctness. However, verbalized confidence is calibrated at the
token level and thus exhibits inconsistency across textual variations with same semantic meaning. We propose Calibration with Semantic Reward (CSR), a framework that calibrates
language models directly in semantic space without a verbalized confidence interface. CSR combines the correctness reward with a novel semantic calibration reward that encourages exploitation among correct rollouts by promoting semantic agreement, and exploration among incorrect ones by discouraging spurious consistency. Experiments across three model families on HotpotQA (in-distribution) and TriviaQA, MSMARCO, and NQ-Open (out-of-distribution) show that CSR consistently achieves lower ECE and higher AUROC than verbalized-confidence baselines across nearly all settings, reducing ECE by up to $40\%$ and improving AUROC by up to $31\%$ over verbalized-confidence baselines, with calibration behavior generalizing robustly across all four evaluation settings.
Read the full abstract ▾
All authors Fengfei Yu, Ruijia Niu, Dongxia Wu, Yian Ma, Rose Yu
Computation and Language
Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems
Nurbek Tastan, Alex Iacob, Lorenzo Sani et al. (+4 more)
Multi-
agent systems can solve complex tasks through collaboration between multiple Large
Language Model
agents. Existing collaboration frameworks typically operate in either a parallel or a sequential mode. In the parallel mode,
agents respond independently to queries followed by aggregation of responses. In contrast, sequential systems allow
agents to communicate via a directed
topology and refine one another step by step. However, both modes are inadequate for achieving the desired objectives of minimizing communication and latency while simultaneously maximizing the accuracy of the final response. In this work, we introduce a hybrid paradigm called Nexa, a trainable response-conditioned policy that bridges the gap between the two modes. Nexa begins with a parallel execution stage, embeds the resulting responses into a shared semantic space, and then predicts a sparse directed acyclic communication graph. If the graph is empty, the system remains purely parallel; if it is non-empty, the system performs one sequential message propagation. The policy is a lightweight
transformer model, and the method avoids the need for external LLM judges or reward models, as well as hand-crafted test-time
topology search. We formalize this hybrid execution problem, show that the resulting graph is acyclic by construction, and that the framework strictly subsumes pure parallel execution, and present a training procedure based on policy-gradient optimization. Results demonstrate that the response-conditioned policy learned by Nexa under one setting can be reused when the number of
agents, the task, or the underlying
agent changes, thus emphasizing the generalizability of the learned communication policy.
Read the full abstract ▾
All authors Nurbek Tastan, Alex Iacob, Lorenzo Sani, Meghdad Kurmanji, Nicholas D. Lane, Samuel Horvath, Karthik Nandakumar
Computation and Language
Measuring Maximum Activations in Open Large Language Models
Luxuan Chen, Han Tian, Xinran Chen et al. (+9 more)
The dynamic range of activations is a first-order constraint for low-bit quantization, activation scaling, and stable LLM inference. Prior work characterized outlier features and massive activations on pre-2024 LLaMA-style models, and the downstream activation-quantization stack inherits that picture without revisiting it for the post-LLaMA open-model boom. We ask the deployment-oriented question: how large can activations get in modern open LLMs, and how does this magnitude vary across families, generations, and training stages? Under a unified pipeline (5,000-sample multi-domain corpus, family-specific tokenization, identical hooks across
embeddings, hidden states,
attention, MLP/MoE, SwiGLU gates, and final norm), we measure global and layerwise maxima on 27 checkpoints from 8 open families spanning dense, MoE,
vision-
language, intermediate-training, and instruction-tuned variants. We find that (i) global maxima span over nearly four orders of magnitude at comparable parameter counts, with Qwen3.5 and MoE checkpoints in the 10^2 to 10^3 range and Gemma3-27B-it reaching ~7 x 10^5; (ii) cross-family and cross-generation comparisons break simple monotonic scaling; and (iii) MoE checkpoints exhibit 14.0-23.4x lower peaks than matched-scale dense counterparts, while the residual stream carries the global maximum in 22/24 checkpoints. A lightweight INT-8 sanity check shows that measured maxima co-vary with low-bit reconstruction error via activation-scale selection. We conclude that maximum activation magnitude is a model property tied to family, architecture, and training stage - not a simple byproduct of size - and should be measured and reported alongside any open-weight release before low-bit deployment. The code is publicly available at https://github.com/clx1415926/Max_act_llm.
Read the full abstract ▾
All authors Luxuan Chen, Han Tian, Xinran Chen, Rui Kong, Fang Wang, Jiamin Chen, Yuchen Li, Jiashu Zhao, Shuaiqiang Wang, Haoyi Xiong, Linghe Kong, Dawei Yin