Computation and Language
ReGuLaR: Variational Latent Reasoning Guided by Rendered Chain-of-Thought
Fanmeng Wang, Haotian Liu, Guojiang Zhao et al. (+2 more)
While Chain-of-Thought (CoT) significantly enhances the performance of Large
Language Models (LLMs), explicit
reasoning chains introduce substantial computational redundancy. Recent latent
reasoning methods attempt to mitigate this by compressing
reasoning processes into latent space, but often suffer from severe performance degradation due to the lack of appropriate compression guidance. In this study, we propose Rendered CoT-Guided variational Latent
Reasoning (ReGuLaR), a simple yet novel latent learning paradigm resolving this issue. Fundamentally, we formulate latent
reasoning within the Variational Auto-Encoding (VAE) framework, sampling the current latent
reasoning state from the posterior distribution conditioned on previous ones. Specifically, when learning this variational latent
reasoning model, we render explicit
reasoning chains as images, from which we extract dense visual-semantic representations to regularize the posterior distribution, thereby achieving efficient compression with minimal information loss. Extensive experiments demonstrate that ReGuLaR significantly outperforms existing latent
reasoning methods across both computational efficiency and
reasoning effectiveness, and even surpasses CoT through multi-modal
reasoning, providing a new and insightful solution to latent
reasoning. Code: https://github.com/FanmengWang/ReGuLaR.
Read the full abstract ▾
All authors Fanmeng Wang, Haotian Liu, Guojiang Zhao, Hongteng Xu, Zhifeng Gao
Computation and Language
JobResQA: A Benchmark for LLM Machine Reading Comprehension on Multilingual Résumés and JDs
Casimiro Pio Carrino, Paula Estrella, Rabih Zbib et al. (+2 more)
We introduce JobResQA, a
multilingual Question Answering
benchmark for evaluating Machine Reading Comprehension (MRC) capabilities of LLMs on HR-specific tasks involving résumés and job descriptions. The
dataset comprises 581 QA pairs across 105 synthetic résumé-job description pairs in five
languages (English, Spanish, Italian, German, and Chinese), with questions spanning three complexity levels from basic factual extraction to complex cross-document
reasoning. We propose a data generation pipeline derived from real-world sources through de-identification and data synthesis to ensure both realism and
privacy, while controlled demographic and professional attributes (implemented via placeholders) enable systematic bias and
fairness studies. We also present a cost-effective, human-in-the-loop translation pipeline based on the TEaR methodology, incorporating MQM error annotations and selective post-editing to ensure an high-quality multi-way parallel
benchmark. We provide a baseline evaluations across multiple open-weight LLM families using an LLM-as-judge approach revealing higher performances on English and Spanish but substantial degradation for other
languages, highlighting critical gaps in
multilingual MRC capabilities for HR applications. JobResQA provides a reproducible
benchmark for advancing fair and reliable LLM-based HR systems. The
benchmark is publicly available at: https://github.com/Avature/jobresqa-
benchmark
Read the full abstract ▾
All authors Casimiro Pio Carrino, Paula Estrella, Rabih Zbib, Carlos Escolano, José A. R. Fonollosa
Computation and Language
FourierSampler: Unlocking Non-Autoregressive Potential in Diffusion Language Models via Frequency-Guided Generation
Siyang He, Qiqi Wang, Xiaoran Liu et al. (+8 more)
Despite the non-autoregressive potential of
diffusion language models (dLLMs), existing decoding strategies demonstrate positional bias, failing to fully unlock the potential of arbitrary generation. In this work, we delve into the inherent spectral characteristics of dLLMs and present the first frequency-domain analysis showing that low-frequency components in hidden states primarily encode global structural information and long-range dependencies, while high-frequency components are responsible for characterizing local details. Based on this observation, we propose FourierSampler, which leverages a frequency-domain sliding window mechanism to dynamically guide the model to achieve a "structure-to-detail" generation. FourierSampler outperforms other inference enhancement strategies on LLADA and SDAR, achieving relative improvements of 20.4% on LLaDA1.5-8B and 16.0% on LLaDA-8B-Instruct. It notably surpasses similarly sized autoregressive models like Llama3.1-8B-Instruct.
Read the full abstract ▾
All authors Siyang He, Qiqi Wang, Xiaoran Liu, Hongnan Ma, Yiwei Shi, Yuerong Song, Ying Zhu, Tianyi Liang, Zengfeng Huang, Ziwei He, Xipeng Qiu
Computation and Language
Monotonic Reference-Free Refinement for Autoformalization
Lan Zhang, Marco Valentino and André Freitas
While statement autoformalization has advanced rapidly, full-
theorem autoformalization remains largely unexplored. Existing iterative refinement methods in statement autoformalization typically improve isolated aspects of formalization, such as syntactic correctness, but struggle to jointly optimize multiple quality dimensions, which is critical for full-
theorem autoformalization. We introduce a reference-free iterative monotonic process at inference time for full-
theorem autoformalization that leverages complementary feedback from
theorem provers and LLM-based judges, without access to ground-truth or existing formalizations and without human intervention. Our approach optimizes a masked composite objective over Formal Validity, Logical Preservation, Mathematical Consistency, and Formal Quality, guided by a responsiveness map that indicates how different LLMs acting as different roles preferentially improve each dimension. We further propose an acceptance policy that guarantees certified monotonic improvement, and provide conditions ensuring convergence and termination. Empirical experiments demonstrate the proposed process enables simultaneous improvement across multiple dimensions, achieving 100.00% formal validity and a 90.27% overall score on miniF2F, and 77.96% formal validity and a 52.45% overall score on ProofNet.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.SD
DIFFA-2: A Practical Diffusion Large Language Model for General Audio Understanding
Jiaming Zhou, Xuxin Cheng, Shiwan Zhao et al. (+5 more)
Autoregressive (AR) large audio
language models (LALMs) such as Qwen-2.5-Omni have achieved strong performance on audio understanding and interaction, but scaling them remains costly in data and computation, and strictly sequential decoding limits inference efficiency.
Diffusion large
language models (dLLMs) have recently been shown to make effective use of limited training data, and prior work on DIFFA indicates that replacing an AR backbone with a
diffusion counterpart can substantially improve audio understanding under matched settings, albeit at a proof-of-concept scale without large-scale instruction tuning, preference
alignment, or practical decoding schemes. We introduce DIFFA-2, a practical
diffusion-based LALM for general audio understanding. DIFFA-2 upgrades the
speech encoder, employs dual semantic and acoustic adapters, and is trained with a four-stage curriculum that combines semantic and acoustic
alignment, large-scale supervised fine-tuning, and variance-reduced preference optimization, using only fully open-source corpora. Experiments on MMSU, MMAU, and MMAR show that DIFFA-2 consistently improves over DIFFA and is competitive to strong AR LALMs under practical training budgets, supporting
diffusion-based modeling is a viable backbone for large-scale audio understanding. Our code is available at https://github.com/NKU-HLT/DIFFA.git.
Read the full abstract ▾
All authors Jiaming Zhou, Xuxin Cheng, Shiwan Zhao, Yuhang Jia, Cao Liu, Ke Zeng, Xunliang Cai, Yong Qin
Computation and Language
Evaluating the Utility of Grounding Documents with Reference-Free LLM-based Metrics
Yilun Hua, Giuseppe Castellucci, Peter Schulam et al. (+2 more)
Retrieval Augmented Generation (RAG)'s success depends on the utility the LLM derives from the content used for grounding. Quantifying content utility does not have a definitive specification and existing metrics ignore model-specific capabilities and/or rely on costly annotations. In this paper, we propose Grounding Generation Utility (GroGU), a model-specific and reference-free metric that defines utility as a function of the downstream LLM's generation confidence based on
entropy. Despite having no annotation requirements, GroGU is largely faithful in distinguishing ground-truth documents while capturing nuances ignored by LLM-agnostic metrics. We apply GroGU to train a query-rewriter for RAG by identifying high-utility preference data for Direct Preference Optimization. Experiments show improvements by up to 18.2 points in Mean Reciprocal Rank and up to 9.4 points in answer accuracy.
Read the full abstract ▾
All authors Yilun Hua, Giuseppe Castellucci, Peter Schulam, Heba Elfardy, Kevin Small
Computation and Language
Safer Policy Compliance with Dynamic Epistemic Fallback
Joseph Marvin Imperial and Harish Tayyar Madabushi
Humans develop a series of cognitive defenses, known as epistemic vigilance, to combat risks of deception and misinformation from everyday interactions. Developing safeguards for LLMs inspired by this mechanism might be particularly helpful for their application in high-stakes tasks such as automating compliance with data
privacy laws. In this paper, we introduce Dynamic Epistemic Fallback (DEF), a dynamic safety protocol for improving an LLM's inference-time defenses against deceptive attacks that make use of maliciously perturbed policy texts. Through various levels of one-sentence textual cues, DEF nudges LLMs to flag inconsistencies, refuse compliance, and fallback to their parametric knowledge upon encountering perturbed policy texts. Using globally recognized legal policies such as HIPAA and GDPR, our empirical evaluations report that DEF effectively improves the capability of frontier LLMs to detect and refuse perturbed versions of policies, with DeepSeek-R1 achieving a 100% detection rate in one setting. This work encourages further efforts to develop cognitively inspired defenses to improve LLM robustness against forms of harm and deception that exploit legal artifacts.
Read the full abstract ▾
Computation and Language
Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
Yanghao Su, Wenbo Zhou, Tianwei Zhang et al. (+4 more)
Emergent Misalignment refers to a failure mode in which fine-tuning large
language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mainly attribute this phenomenon to the generalization of erroneous or unsafe content. In this work, we show that this view is incomplete. Across multiple domains and model families, we find that fine-tuning models on data exhibiting specific character-level dispositions induces substantially stronger and more transferable misalignment than incorrect-advice fine-tuning, while largely preserving general capabilities. This indicates that emergent misalignment arises from stable shifts in model behavior rather than from capability degradation or corrupted knowledge. We further show that such behavioral dispositions can be conditionally activated by both training-time triggers and inference-time persona-aligned
prompts, revealing shared structure across emergent misalignment,
backdoor activation, and jailbreak susceptibility. Overall, our results identify character formation as a central and underexplored
alignment risk, suggesting that robust
alignment must address behavioral dispositions rather than isolated errors or
prompt-level defenses.
Read the full abstract ▾
All authors Yanghao Su, Wenbo Zhou, Tianwei Zhang, Qiu Han, Weiming Zhang, Nenghai Yu, Jie Zhang
Computation and Language
DimABSA: Building Multilingual and Multidomain Datasets for Dimensional Aspect-Based Sentiment Analysis
Lung-Hao Lee, Liang-Chih Yu, Natalia Loukashevich et al. (+13 more)
Aspect-Based Sentiment Analysis (ABSA) focuses on extracting sentiment at a fine-grained aspect level and has been widely applied across real-world domains. However, existing ABSA research relies on coarse-grained categorical labels (e.g., positive, negative), which limits its ability to capture nuanced affective states. To address this limitation, we adopt a dimensional approach that represents sentiment with continuous valence-arousal (VA) scores, enabling fine-grained analysis at both the aspect and sentiment levels. To this end, we introduce DimABSA, the first
multilingual, dimensional ABSA resource annotated with both traditional ABSA elements (aspect terms, aspect categories, and opinion terms) and newly introduced VA scores. This resource contains 76,958 aspect instances across 42,590 sentences, spanning six
languages and four domains. We further introduce three subtasks that combine VA scores with different ABSA elements, providing a bridge from traditional ABSA to dimensional ABSA. Given that these subtasks involve both categorical and continuous outputs, we propose a new unified metric, continuous F1 (cF1), which incorporates VA prediction error into standard F1. We provide a comprehensive
benchmark using both prompted and fine-tuned large
language models across all subtasks. Our results show that DimABSA is a challenging
benchmark and provides a foundation for advancing
multilingual dimensional ABSA. We publicly released the DimABSA
dataset, which was used for Track A of SemEval-2026 Task 3, attracting over 300 participants.
Read the full abstract ▾
All authors Lung-Hao Lee, Liang-Chih Yu, Natalia Loukashevich, Ilseyar Alimova, Alexander Panchenko, Tzu-Mi Lin, Zhe-Yu Xu, Jian-Yu Zhou, Guangmin Zheng, Jin Wang, Sharanya Awasthi, Jonas Becker, Jan Philip Wahle, Terry Ruas, Shamsuddeen Hassan Muhammad, Saif M. Mohammad
Computation and Language · Cross-listed from cs.LG
Mem-T: Densifying Rewards for Long-Horizon Memory Agents
Yanwei Yue, Boci Peng, Xuanbo Fan et al. (+3 more)
Memory agents, which depart from predefined
memory-processing pipelines by endogenously managing the processing, storage, and
retrieval of
memories, have garnered increasing
attention for their autonomy and adaptability. However, existing training paradigms remain constrained:
agents often traverse long-horizon sequences of
memory operations before receiving sparse and delayed rewards, which hinders truly end-to-end optimization of
memory management policies. To address this limitation, we introduce Mem-T, an autonomous
memory agent that interfaces with a lightweight hierarchical
memory database to perform dynamic updates and multi-turn
retrieval over streaming inputs. To effectively train long-horizon
memory management capabilities, we further propose MoT-GRPO, a tree-guided reinforcement learning framework that transforms sparse terminal feedback into dense, step-wise supervision via
memory operation tree backpropagation and hindsight credit assignment, thereby enabling the joint optimization of
memory construction and
retrieval. Extensive experiments demonstrate that Mem-T is (1) high-performing, surpassing frameworks such as A-Mem and Mem0 by up to $14.92\%$, and (2) economical, operating on a favorable accuracy-efficiency Pareto frontier and reducing inference
tokens per query by $\sim24.45\%$ relative to GAM without sacrificing performance.
Read the full abstract ▾
All authors Yanwei Yue, Boci Peng, Xuanbo Fan, Jiaxin Guo, Qiankun Li, Yan Zhang
Computation and Language
InstructDiff: Domain-Adaptive Data Selection via Differential Entropy for Efficient LLM Fine-Tuning
Junyou Su, He Zhu, Xiao Luo et al. (+6 more)
Supervised fine-tuning (SFT) is fundamental to adapting large
language models, yet training on complete
datasets incurs prohibitive costs with diminishing returns. Existing data selection methods suffer from severe domain specificity: techniques optimized for general instruction-following fail on
reasoning tasks, and vice versa. We observe that measuring
entropy differences between base models and minimally instruction-tuned calibrated models reveals a pattern – samples with the lowest differential
entropy consistently yield optimal performance across domains, yet this principle manifests domain-adaptively:
reasoning tasks favor
entropy increase (cognitive expansion), while general tasks favor
entropy decrease (cognitive compression). We introduce InstructDiff, a unified framework that operationalizes differential
entropy as a domain-adaptive selection criterion through warmup calibration, bi-directional NLL filtering, and
entropy-based ranking. Extensive experiments show that InstructDiff achieves 17% relative improvement over full data training on mathematical
reasoning and 52% for general instruction-following, outperforming prior baselines while using only 10% of the data.
Read the full abstract ▾
All authors Junyou Su, He Zhu, Xiao Luo, Liyu Zhang, Hong-Yu Zhou, Yun Chen, Peng Li, Yang Liu, Guanhua Chen
Computation and Language
Bias Beyond Borders: Political Ideology Evaluation and Steering in Multilingual LLMs
Afrozah Nadeem, Agrima Seth, Mehwish Nasim et al. (+1 more)
Large
Language Models (LLMs) increasingly shape global discourse, making
fairness and ideological neutrality essential for responsible AI deployment. Despite growing
attention to political bias in LLMs, prior work largely focuses on high-resource, Western
languages or narrow
multilingual settings, leaving cross-lingual consistency and safe post-hoc mitigation underexplored. To address this gap, we present a large-scale
multilingual evaluation of political bias spanning 50 countries and 33
languages. We introduce a complementary post-hoc mitigation framework, Cross-Lingual
Alignment Steering (CLAS), designed to augment existing steering methods by aligning ideological representations across
languages and dynamically regulating intervention strength. This method aligns latent ideological representations induced by political
prompts into a shared ideological subspace, ensuring cross lingual consistency, with the adaptive mechanism prevents over correction and preserves coherence. Experiments demonstrate substantial bias reduction along both economic and social axes with minimal degradation in response quality. The proposed framework establishes a scalable and interpretable paradigm for
fairness-aware
multilingual LLM governance, balancing ideological neutrality with linguistic and cultural diversity.
Read the full abstract ▾
All authors Afrozah Nadeem, Agrima Seth, Mehwish Nasim, Usman Naseem
Computation and Language
ArabicDialectHub: A Cross-Dialectal Arabic Learning Resource and Platform
Salem Lahlou
We present ArabicDialectHub, a cross-dialectal Arabic learning resource comprising 552 phrases across six varieties (Moroccan Darija, Lebanese, Syrian, Emirati, Saudi, and MSA) and an interactive web platform. Phrases were generated using LLMs and validated by five native speakers, stratified by difficulty, and organized thematically. The open-source platform provides translation exploration, adaptive quizzing with algorithmic distractor generation, cloud-synchronized progress tracking, and cultural context. Both the
dataset and complete platform source code are released under MIT license. Platform: https://arabic-dialect-hub.netlify.app.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.LG
Learnable Permutation for Structured Sparsity on Transformer Models
Zekai Li, Ji Liu, Guanchen Li et al. (+5 more)
Structured sparsity has emerged as a popular model
pruning technique, widely adopted in various architectures, including CNNs,
Transformer models, and especially large
language models (LLMs) in recent years. A promising direction to further improve post-
pruning performance is weight permutation, which reorders model weights into patterns more amenable to
pruning. However, the exponential growth of the permutation search space with the scale of
Transformer architectures forces most methods to rely on greedy or heuristic
algorithms, limiting the effectiveness of reordering. In this work, we propose a novel end-to-end learnable permutation framework. Our method introduces a learnable permutation cost
matrix to quantify the cost of swapping any two input channels of a given weight
matrix, a differentiable bipartite matching solver to obtain the optimal binary permutation
matrix given a cost
matrix, and a sparsity optimization loss function to directly optimize the permutation operator. We extensively validate our approach on
vision and
language Transformers, demonstrating that our method achieves state-of-the-art permutation results for structured sparsity.
Read the full abstract ▾
All authors Zekai Li, Ji Liu, Guanchen Li, Yixing Xu, Ziqiong Liu, Xuanwu Yin, Dong Li, Emad Barsoum
Computation and Language · Cross-listed from cs.ET
MiTa: A Hierarchical Multi-Agent Collaboration Framework with Memory-integrated and Task Allocation
XiaoJie Zhang, JianHan Wu, Xiaoyang Qu et al. (+1 more)
Recent advances in large
language models (LLMs) have substantially accelerated the development of
embodied agents. LLM-based multi-
agent systems mitigate the inefficiency of single
agents in complex tasks. However, they still suffer from issues such as
memory inconsistency and
agent behavioral conflicts. To address these challenges, we propose MiTa, a hierarchical
memory-integrated task allocative framework to enhance collaborative efficiency. MiTa organizes
agents into a manager-member hierarchy, where the manager incorporates additional allocation and summary modules that enable (1) global task allocation and (2) episodic
memory integration. The allocation module enables the manager to allocate tasks from a global perspective, thereby avoiding potential inter-
agent conflicts. The summary module, triggered by task progress updates, performs episodic
memory integration by condensing recent collaboration history into a concise summary that preserves long-horizon context. By combining task allocation with episodic
memory, MiTa attains a clearer understanding of the task and facilitates globally consistent task distribution. Experimental results confirm that MiTa achieves superior efficiency and adaptability in complex multi-
agent cooperation over strong baseline methods.
Read the full abstract ▾
All authors XiaoJie Zhang, JianHan Wu, Xiaoyang Qu, Jianzong Wang
Computation and Language
A Unified View of Attention and Residual Sinks: Outlier-Driven Rescaling is Essential for Transformer Training
Zihan Qiu, Zeyu Huang, Kaiyue Wen et al. (+16 more)
We investigate the functional role of emergent outliers in large
language models, specifically
attention sinks (a few
tokens that consistently receive large
attention logits) and residual sinks (a few fixed dimensions with persistently large activations across most
tokens). We hypothesize that these outliers, in conjunction with the corresponding normalizations (e.g., softmax
attention and RMSNorm), effectively rescale other non-outlier components. We term this phenomenon outlier-driven rescaling and validate this hypothesis across different model architectures and training
token counts. This view unifies the origin and mitigation of both sink types. Our main conclusions and observations include: (1) Outliers function jointly with normalization: removing normalization eliminates the corresponding outliers but degrades training stability and performance; directly clipping outliers while retaining normalization leads to degradation, indicating that outlier-driven rescaling contributes to training stability. (2) Outliers serve more as rescale factors rather than contributors, as the final contributions of
attention and residual sinks are significantly smaller than those of non-outliers. (3) Outliers can be absorbed into learnable parameters or mitigated via explicit gated rescaling, leading to improved training performance (average gain of 2 points) and enhanced quantization robustness (1.2 points degradation under W4A4 quantization).
Read the full abstract ▾
All authors Zihan Qiu, Zeyu Huang, Kaiyue Wen, Peng Jin, Bo Zheng, Yuxin Zhou, Haofeng Huang, Zekun Wang, Xiao Li, Huaqing Zhang, Yang Xu, Haoran Lian, Siqi Zhang, Rui Men, Jianwei Zhang, Ivan Titov, Dayiheng Liu, Jingren Zhou, Junyang Lin
Computation and Language
Yuezhou Hu, Harman Singh, Monishwaran Maheswaran et al. (+10 more)
Diffusion Large
Language Models (dLLMs) have emerged as a promising alternative to purely autoregressive
language models because they can decode multiple
tokens in parallel. However, state-of-the-art block-wise dLLMs rely on a "remasking" mechanism that decodes only the most confident
tokens and discards the rest, effectively wasting computation. We demonstrate that recycling computation from the discarded
tokens is beneficial, as these
tokens retain contextual information useful for subsequent decoding iterations. In light of this, we propose Residual Context
Diffusion (RCD), a module that converts these discarded
token representations into contextual residuals and injects them back for the next denoising step. RCD uses a decoupled two-stage training pipeline to bypass the
memory bottlenecks associated with backpropagation. We validate our method on both long CoT
reasoning (SDAR) and short CoT instruction following (LLaDA) models. We demonstrate that a standard dLLM can be efficiently converted to the RCD paradigm with merely ~300 million
tokens. RCD consistently improves frontier dLLMs by 4-11 percentage points in accuracy with minimal extra computation overhead across a wide range of
benchmarks. Notably, on the most challenging AIME tasks, RCD nearly doubles baseline accuracy and attains up to 4-5x fewer denoising steps at baseline's peak accuracy.
Read the full abstract ▾
All authors Yuezhou Hu, Harman Singh, Monishwaran Maheswaran, Haocheng Xi, Coleman Hooper, Jintao Zhang, Aditya Tomar, Michael W. Mahoney, Sewon Min, Mehrdad Farajtabar, Kurt Keutzer, Amir Gholami, Chenfeng Xu
Computation and Language · Cross-listed from cs.LG
Perplexity Cannot Always Tell Right from Wrong
Petar Veličković, Federico Barbero, Christos Perivolaropoulos et al. (+2 more)
Perplexity – a function measuring a model's overall level of "surprise" when encountering a particular output – has gained significant traction in recent years, both as a loss function and as a simple-to-compute metric of model quality. Prior studies have pointed out several limitations of perplexity, often from an empirical manner. Here we leverage recent results on
Transformer continuity to show in a rigorous manner how perplexity may be an unsuitable metric for model selection. Specifically, we prove that, if there is any sequence that a compact decoder-only
Transformer model predicts accurately and confidently – a necessary pre-requisite for strong generalisation – it must imply existence of another sequence with very low perplexity, but not predicted correctly by that same model. Further, by analytically studying iso-perplexity plots, we find that perplexity will not always select for the more accurate model – rather, any increase in model confidence must be accompanied by a commensurate rise in accuracy for the new model to be selected.
Read the full abstract ▾
All authors Petar Veličković, Federico Barbero, Christos Perivolaropoulos, Simon Osindero, Razvan Pascanu
Computation and Language
Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection
Yuan Li, Jun Hu, Bryan Hooi et al. (+2 more)
Graph-based fraud detection on text-attributed graphs (TAGs) requires jointly modeling rich textual semantics and relational dependencies. However, existing LLM-enhanced GNN approaches are constrained by predefined prompting and decoupled training pipelines, limiting
reasoning autonomy and weakening semantic-structural
alignment. We propose FraudCoT, a unified framework that advances TAG-based fraud detection through autonomous, graph-aware chain-of-thought (CoT)
reasoning and scalable LLM-GNN co-training. To address the limitations of predefined
prompts, we introduce a fraud-aware selective CoT
distillation mechanism that generates diverse
reasoning paths and enhances semantic-structural understanding. These distilled CoTs are integrated into node texts, providing GNNs with enriched, multi-hop semantic and structural cues for fraud detection. Furthermore, we develop an efficient asymmetric co-training strategy that enables end-to-end optimization while significantly reducing the computational cost of naive joint training. Extensive experiments on public and industrial
benchmarks demonstrate that FraudCoT achieves up to 8.8% AUPRC improvement over state-of-the-art methods and delivers up to 1,066x speedup in training throughput, substantially advancing both detection performance and efficiency.
Read the full abstract ▾
All authors Yuan Li, Jun Hu, Bryan Hooi, Bingsheng He, Cheng Chen
Computation and Language
Reconsidering Positional Supervision in Masked Diffusion Language Model Training
Mengyu Ye, Keito Kudo, Ryosuke Takahashi et al. (+1 more)
Masked
diffusion language models (MDLMs) generate text by unmasking
tokens in parallel and have recently emerged as alternatives to autoregressive
language models. They can be viewed as parallel decoders trained with a position-wise cross-
entropy (CE) loss, the same setup as non-autoregressive translation (NAT). In NAT, CE-trained parallel decoders have been argued to be sensitive to small positional shifts, since CE penalizes them harshly. We ask whether CE-trained MDLMs are similarly sensitive to such shifts under iterative decoding. To probe this, we apply a controlled intervention that introduces them during decoding. On LLaDA-8B-Instruct with Arena-Hard, displacing as little as 1% of generated
tokens by one position substantially reduces win rates against the unintervened model, showing that MDLMs are sensitive to such small shifts under iterative parallel decoding. Motivated by this, we adapt connectionist temporal classification (CTC), an
alignment-flexible objective known to mitigate it there, to MDLM supervised fine-tuning. By relaxing the strict position-wise match that CE imposes, CTC gives the loss room to absorb small positional shifts; concretely, we modified CTC objective to use a special <slack>
token that absorbs positional uncertainty between target
tokens and output positions, and a updated collapse map that preserves target surface forms. Across four open-ended generation
benchmarks, the resulting model consistently improves over both the original model and a matched cross-
entropy-trained baseline, with statistically significant gains on all four. These results identify training-side
alignment flexibility as a useful design dimension for MDLM SFT, complementary to the inference-time approaches explored in prior work.
Read the full abstract ▾
All authors Mengyu Ye, Keito Kudo, Ryosuke Takahashi, Jun Suzuki
Computation and Language
Benchmarking Machine Translation on Chinese Social Media Texts
Kaiyan Zhao, Zheyong Xie, Zhongtao Miao et al. (+3 more)
The prevalence of rapidly evolving slang, neologisms, and highly stylized expressions in informal user-generated text, particularly on Chinese social media, poses significant challenges for Machine Translation (MT) benchmarking. Specifically, we identify two primary obstacles: (1) data scarcity, as high-quality parallel data requires bilingual annotators familiar with platform-specific slang, and stylistic cues in both
languages; and (2) metric limitations, where traditional evaluators like COMET often fail to capture stylistic fidelity and nonstandard expressions. To bridge these gaps, we introduce CSM-MTBench, a
benchmark covering five Chinese-foreign
language directions and consisting of two expert-curated subsets: Fun Posts, featuring context-rich, slang- and neologism-heavy content, and Social Snippets, emphasizing concise,
emotion- and style- driven expressions. Furthermore, we propose tailored evaluation approaches for each subset: measuring the translation success rate of slang and neologisms in Fun Posts, while assessing tone and style preservation in Social Snippets via a hybrid of
embedding-based metrics and LLM-as-a-judge. Experiments on over 20 models reveal substantial variation in how current MT systems handle semantic fidelity and informal, social-media-specific stylistic cues. CSM-MTBench thus serves as a rigorous testbed for advancing MT systems capable of mastering real-world Chinese social media texts.
Read the full abstract ▾
All authors Kaiyan Zhao, Zheyong Xie, Zhongtao Miao, Xinze Lyu, Yao Hu, Shaosheng Cao
Computation and Language · Cross-listed from cs.CV
Semantic Leakage from Image Embeddings
Yiyi Chen, Qiongkai Xu, Desmond Elliott et al. (+2 more)
Image
embeddings are generally assumed to pose limited
privacy risk. We challenge this assumption by formalizing semantic leakage as the ability to recover semantic structures from compressed image
embeddings. Surprisingly, we show that semantic leakage does not require exact reconstruction of the original image. Preserving local semantic neighborhoods under
embedding alignment is sufficient to expose the intrinsic vulnerability of image
embeddings. Crucially, this preserved neighborhood structure allows semantic information to propagate through a sequence of lossy mappings. Based on this
conjecture, we propose Semantic Leakage from Image
Embeddings (SLImE), a lightweight inference framework that reveals semantic information from standalone compressed image
embeddings, incorporating a locally trained semantic retriever with off-the-shelf models, without training task-specific decoders. We thoroughly validate each step of the framework empirically, from aligned
embeddings to retrieved tags, symbolic representations, and grammatical and coherent descriptions. We evaluate SLImE across a range of open and closed
embedding models, including GEMINI, COHERE, NOMIC, and CLIP, and demonstrate consistent recovery of semantic information across diverse inference tasks. Our results reveal a fundamental vulnerability in image
embeddings, whereby the preservation of semantic neighborhoods under
alignment enables semantic leakage, highlighting challenges for
privacy preservation.1
Read the full abstract ▾
All authors Yiyi Chen, Qiongkai Xu, Desmond Elliott, Qiongxiu Li, Johannes Bjerva
Computation and Language
LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models
Alhassan Abdelhalim, Janick Edinger, Sören Laue et al. (+1 more)
Large
Language Models (LLMs) are becoming increasingly popular in pervasive computing due to their versatility and strong performance. However, despite their ubiquitous use, the exact mechanisms underlying their outstanding performance remain unclear. Different methods for LLM explainability exist, and many are, as a method, not fully understood themselves. We started with the question of how linguistic abstraction emerges in LLMs, aiming to detect it across different LLM modules (
attention heads and input
embeddings). For this, we used methods well-established in the literature: (1) probing for
token-level relational structures, and (2) feature-mapping using
embeddings as carriers of human-interpretable properties. Both attempts failed for different methodological reasons:
Attention-based explanations collapsed once we tested the core assumption that later-layer representations still correspond to
tokens. Property-inference methods applied to
embeddings also failed because their high predictive scores were driven by methodological artifacts and
dataset structure rather than meaningful semantic knowledge. These failures matter because both techniques are widely treated as evidence for what LLMs supposedly understand, yet our results show such conclusions are unwarranted. These limitations are particularly relevant in pervasive and distributed computing settings where LLMs are deployed as system components and interpretability methods are relied upon for debugging, compression, and explaining models.
Read the full abstract ▾
All authors Alhassan Abdelhalim, Janick Edinger, Sören Laue, Michaela Regneri
Computation and Language
DiffuSpeech: Silent Thought, Spoken Answer via Unified Speech-Text Diffusion
Yuxuan Lou, Ziming Wu, Yaochen Wang et al. (+6 more)
Current
speech language models generate responses directly without explicit
reasoning, leading to errors that cannot be corrected once audio is produced. We introduce “Silent Thought, Spoken Answer” – a paradigm where
speech LLMs generate internal text
reasoning alongside spoken responses, with thinking traces informing
speech quality. To realize this, we present \method{}, the first
diffusion-based
speech-text
language model supporting both understanding and generation, unifying discrete text and tokenized
speech under a single masked
diffusion framework. Unlike autoregressive approaches, \method{} jointly generates
reasoning traces and
speech tokens through iterative denoising, with modality-specific masking schedules. We also construct \dataset{}, the first
speech QA
dataset with paired text
reasoning traces, containing 26K samples totaling 319 hours. Experiments show \method{} achieves state-of-the-art
speech-to-
speech QA accuracy, outperforming the best baseline by up to 9 points, while attaining the best TTS quality among generative models (6.2% WER) and preserving
language understanding (66.2% MMLU). Ablations confirm that both the
diffusion architecture and thinking traces contribute to these gains.
Read the full abstract ▾
All authors Yuxuan Lou, Ziming Wu, Yaochen Wang, Yong Liu, Yingxuan Ren, Fuming Lai, Shaobing Lian, Jie Tang, Yang You
Computation and Language
DialectLLM: A Dialect-Aware Dialog[ue] Generation Framework Beyond Standard American English
Jio Oh, Paul Vicinanza, Thomas Butler et al. (+3 more)
More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects and generate stereotyped responses for their speakers. We introduce DialectLLM, the first large-scale framework for generating high-quality multi-dialectal conversational data encompassing the three pillars of written dialect – lexical (vocabulary), orthographic (spelling), and morphosyntactic (grammar) features. DialectLLM produces a dialect-parallel dialog
dataset spanning nine English dialects. Partnering with native linguists, we design and validate SAE-to-dialect transformation rules, ensuring authenticity. Our approach challenges the prevailing practice of applying a single morphosyntactic feature set to both user utterances and model responses, showing that models should not reproduce up to 90% of the grammatical features of a dialect. Human evaluation confirms data quality, with annotators preferring DialectLLM over prior methods in 98.8% of pairwise comparisons for dialect naturalness. We then construct DialectLLM-Bench, a dialect-parallel
benchmark with 50k+ dialogs, resulting in 97k+ QA pairs, and evaluate 17 LLMs on dialect identification and response generation tasks. Even frontier models achieve under 70% accuracy, fail to reach 50% for prominent dialects like Canadian English, and systematically misclassify non-SAE dialects as American or British. Beyond benchmarking, we show that DialectLLM data also serve as a scalable LLM post-training resource, suggesting a practical path toward dialect-aware conversational AI.
Read the full abstract ▾
All authors Jio Oh, Paul Vicinanza, Thomas Butler, Steven Euijong Whang, Dezhi Hong, Amani Namboori
Computation and Language · Cross-listed from cs.LG
MoVE: Mixture of Value Embeddings – A New Axis for Scaling Parametric Memory in Autoregressive Models
Yangyan Li
Autoregressive sequence modeling stands as the cornerstone of modern Generative AI, powering results across diverse modalities ranging from text generation to image generation. However, a fundamental limitation of this paradigm is the rigid structural coupling of model capacity to computational cost: expanding a model's parametric
memory – its repository of factual knowledge or visual patterns – traditionally requires deepening or widening the network, which incurs a proportional rise in active FLOPs. In this work, we introduce $\textbf{MoVE (Mixture of Value Embeddings)}$, a mechanism that breaks this coupling and establishes a new axis for scaling capacity. MoVE decouples
memory from compute by introducing a global bank of learnable value
embeddings shared across all
attention layers. For every step in the sequence, the model employs a differentiable soft gating mechanism to dynamically mix retrieved concepts from this bank into the standard value projection. This architecture allows parametric
memory to be scaled independently of network depth by simply increasing the number of
embedding slots. We validate MoVE through strictly controlled experiments on two representative applications of autoregressive modeling: Text Generation and Image Generation. In both domains, MoVE yields consistent performance improvements over standard and layer-wise
memory baselines, enabling the construction of "
memory-dense" models that achieve lower perplexity and higher fidelity than their dense counterparts at comparable compute budgets.
Read the full abstract ▾
Computation and Language
Leveraging LLMs For Turkish Skill Extraction
Ezgi Arslan İltüzer, Özgür An{\i}l Özlü, Vahid Farajijobehdar et al. (+1 more)
Skill extraction is a critical component of modern recruitment systems, enabling efficient job matching, personalized recommendations, and labor
market analysis. Despite Türkiye's significant role in the global workforce, Turkish, a morphologically complex
language, lacks both a skill taxonomy and a dedicated skill extraction
dataset, resulting in underexplored research in skill extraction for Turkish. This article seeks the answers to three research questions: 1) How can skill extraction be effectively performed for this
language, in light of its low resource nature? 2)~What is the most promising model? 3) What is the impact of different Large
Language Models (LLMs) and prompting strategies on skill extraction (i.e., dynamic vs. static few-shot samples, varying context information, and encouraging causal
reasoning)? The article introduces the first Turkish skill extraction
dataset and performance evaluations of automated skill extraction using LLMs. The manually annotated
dataset contains 4,819 labeled skill spans from 327 job postings across different occupation areas. The use of LLM outperforms supervised sequence labeling when used in an end-to-end pipeline, aligning extracted spans with standardized skills in the ESCO taxonomy more effectively. The best-performing configuration, utilizing Claude Sonnet 3.7 with dynamic few-shot prompting for skill identification,
embedding-based
retrieval, and LLM-based reranking for skill linking, achieves an end-to-end performance of 0.56, positioning Turkish alongside similar studies in other
languages, which are few in the literature. Our findings suggest that LLMs can improve skill extraction performance in low-resource settings, and we hope that our work will accelerate similar research on skill extraction for underrepresented
languages.
Read the full abstract ▾
All authors Ezgi Arslan İltüzer, Özgür An{\i}l Özlü, Vahid Farajijobehdar, Gülşen Eryiğit
Computation and Language
From Labels to Facets: Building a Taxonomically Enriched Turkish Learner Corpus
Elif Sayar, Tolgahan Türker, Anna Golynskaia Knezhevich et al. (+4 more)
In terms of annotation structure, most learner corpora rely on holistic flat label inventories which, even when extensive, do not explicitly separate multiple linguistic dimensions. This makes linguistically deep annotation difficult and complicates fine-grained analyses aimed at understanding why and how learners produce specific errors. To address these limitations, this paper presents a semi-automated annotation methodology for learner corpora, built upon a recently proposed faceted taxonomy, and implemented through a novel annotation extension framework. The taxonomy provides a theoretically grounded, multi-dimensional categorization that captures the linguistic properties underlying each error instance, thereby enabling standardized, fine-grained, and interpretable enrichment beyond flat annotations. The annotation extension tool, implemented based on the proposed extension framework for Turkish, automatically extends existing flat annotations by inferring additional linguistic and metadata information as facets within the taxonomy to provide richer learner-specific context. It was systematically evaluated and yielded promising performance results, achieving a facet-level accuracy of 95.86%. The resulting taxonomically enriched corpus offers enhanced querying capabilities and supports detailed exploratory analyses across learner corpora, enabling researchers to investigate error patterns through complex linguistic and pedagogical dimensions. This work introduces the first collaboratively annotated and taxonomically enriched Turkish Learner Corpus, a manual annotation guideline with a refined tagset, and an annotation extender. As the first corpus designed in accordance with the recently introduced taxonomy, we expect our study to pave the way for subsequent enrichment efforts of existing error-annotated learner corpora.
Read the full abstract ▾
All authors Elif Sayar, Tolgahan Türker, Anna Golynskaia Knezhevich, Bihter Dereli, Ayşe Demirhas, Lionel Nicolas, Gülşen Eryiğit
Computation and Language · Cross-listed from eess.AS
EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis
Li Zhou, Hao Jiang, Junjie Li et al. (+2 more)
Achieving precise and controllable emotional expression is crucial for producing natural and context-appropriate
speech in text-to-
speech (TTS) synthesis. However, many
emotion-aware TTS systems, including large
language model (LLM)-based designs, rely on scaling fixed
emotion embeddings or external guidance, limiting their ability to model
emotion-specific latent characteristics. To address this gap, we present EmoShift, a lightweight activation-steering framework incorporating a EmoSteer layer, which learns a steering vector for each target
emotion in the output
embedding space to capture its latent offset and maintain stable, appropriate expression across utterances and categories. With only 10M trainable parameters,less than 1/30 of full fine-tuning, EmoShift outperforms zero-shot and fully fine-tuned baselines in objective and subjective evaluations, enhancing emotional expressiveness while preserving naturalness and speaker similarity. Further analysis confirms the proposed EmoSteer layer's effectiveness and reveals its potential for controllable emotional intensity in
speech synthesis.
Read the full abstract ▾
All authors Li Zhou, Hao Jiang, Junjie Li, Tianrui Wang, Haizhou Li
Computation and Language · Cross-listed from cs.CY
Eroding the Truth-Default: A Causal Analysis of Human Susceptibility to Foundation Model Hallucinations and Disinformation in the Wild
Alexander Loth, Martin Kappes and Marc-Oliver Pahl
As foundation models (FMs) approach human-level fluency, distinguishing synthetic from organic content has become a key challenge for Trustworthy Web Intelligence. This paper presents JudgeGPT and RogueGPT, a dual-axis framework that decouples "authenticity" from "attribution" to investigate the mechanisms of human susceptibility. Analyzing 918 evaluations across five FMs (including GPT-4 and Llama-2), we employ Structural Causal Models (SCMs) as a principal framework for formulating testable causal hypotheses about detection accuracy. Contrary to partisan narratives, we find that political orientation shows a negligible association with detection performance ($r=-0.10$). Instead, "fake news familiarity" emerges as a candidate mediator ($r=0.35$), suggesting that exposure may function as
adversarial training for human discriminators. We identify a "fluency trap" where GPT-4 outputs (HumanMachineScore: 0.20) bypass Source Monitoring mechanisms, rendering them indistinguishable from human text. These findings suggest that "pre-bunking" interventions should target cognitive source monitoring rather than demographic
segmentation to ensure trustworthy information ecosystems.
Read the full abstract ▾