Computation and Language
SeLaR: Selective Latent Reasoning in Large Language Models
Renyu Fu and Guibo Luo
Chain-of-Thought (CoT) has become a cornerstone of
reasoning in large
language models, yet its effectiveness is constrained by the limited expressiveness of discrete
token sampling. Recent latent
reasoning approaches attempt to alleviate this limitation by replacing discrete
tokens with soft
embeddings (probability-weighted mixtures of
token embeddings) or hidden states, but they commonly suffer from two issues: (1) global activation injects perturbations into high-confidence steps, impairing
reasoning stability; and (2) soft
embeddings quickly collapse toward the highest-probability
token, limiting exploration of alternative trajectories. To address these challenges, we propose SeLaR (Selective Latent
Reasoning), a lightweight and training-free framework. SeLaR introduces an
entropy-gated mechanism that activates soft
embeddings only at low-confidence steps, while preserving discrete decoding at high-confidence steps. Additionally, we propose an
entropy-aware contrastive regularization that pushes soft
embeddings away from the dominant (highest-probability)
token's direction, encouraging sustained exploration of multiple latent
reasoning paths. Experiments on five
reasoning benchmarks demonstrate that SeLaR consistently outperforms standard CoT and state-of-the-art training-free methods.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
Can Vision Language Models Judge Action Quality? An Empirical Evaluation
Miguel Monte e Freitas, Rui Henriques, Ricardo Rei et al. (+1 more)
Action Quality Assessment (AQA) has broad applications in physical therapy, sports coaching, and competitive judging. Although
Vision Language Models (VLMs) hold considerable promise for AQA, their actual performance in this domain remains largely uncharacterised. We present a comprehensive evaluation of state-of-the-art VLMs across activity domains (e.g. fitness, figure skating, diving), tasks, representations, and prompting strategies. Baseline results reveal that Gemini 3.1 Pro, Qwen3-VL and InternVL3.5 models perform only marginally above random chance, and although strategies such as incorporation of skeleton information, grounding instructions,
reasoning structures and in-context learning lead to isolated gains, none is consistently effective. Analysis of prediction distributions uncovers two systematic biases: a tendency to predict correct execution regardless of visual evidence, and a sensitivity to superficial linguistic framing. Reformulating tasks contrastively to mitigate these biases yields minimal improvement, suggesting that the models' limitations go beyond these biases, pointing to a fundamental difficulty with fine-grained movement quality assessment. Our findings establish a rigorous baseline for future VLM-based AQA research and provide an actionable outline for failure modes requiring mitigation prior to reliable real-world deployment.
Read the full abstract ▾
All authors Miguel Monte e Freitas, Rui Henriques, Ricardo Rei, Pedro Henrique Martins
Computation and Language
Distributed Multi-Layer Editing for Rule-Level Knowledge in Large Language Models
Yating Wang, Wenting Zhao, Yaqi Zhao et al. (+3 more)
Large
language models store not only isolated facts but also rules that support
reasoning across symbolic expressions, natural
language explanations, and concrete instances. Yet most model editing methods are built for fact-level knowledge, assuming that a target edit can be achieved through a localized intervention. This assumption does not hold for rule-level knowledge, where a single rule must remain consistent across multiple interdependent forms. We investigate this problem through a mechanistic study of rule-level knowledge editing. To support this study, we extend the RuleEdit
benchmark from 80 to 200 manually verified rules spanning mathematics and physics. Fine-grained causal tracing reveals a form-specific organization of rule knowledge in
transformer layers: formulas and descriptions are concentrated in earlier layers, while instances are more associated with middle layers. These results suggest that rule knowledge is not uniformly localized, and therefore cannot be reliably edited by a single-layer or contiguous-block intervention. Based on this insight, we propose Distributed Multi-Layer Editing (DMLE), which applies a shared early-layer update to formulas and descriptions and a separate middle-layer update to instances. While remaining competitive on standard editing metrics, DMLE achieves substantially stronger rule-level editing performance. On average, it improves instance portability and rule understanding by 13.91 and 50.19 percentage points, respectively, over the strongest baseline across GPT-J-6B, Qwen2.5-7B, Qwen2-7B, and LLaMA-3-8B. The code is available at https://github.com/Pepper66/DMLE.
Read the full abstract ▾
All authors Yating Wang, Wenting Zhao, Yaqi Zhao, Yongshun Gong, Yilong Yin, Haoliang Sun
Computation and Language
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
Ruotao Xu, Yixin Ji, Yu Luo et al. (+5 more)
Large
reasoning models (LRMs) have achieved strong performance enhancement through scaling test time computation, but due to the inherent limitations of the underlying
language models, they still have shortcomings in tasks that require precise computation and extensive knowledge reserves. Tool-Integrated
Reasoning (TIR) has emerged as a promising paradigm that incorporates tool call and execution within the
reasoning trajectory. Although recent works have released some powerful open-source TIR models, our analysis reveals that these models still suffer from critical deficiencies. We find that when the
reasoning of the model conflicts with the tool results, the model tends to believe in its own
reasoning. And there are cases where the tool results are correct but are ignored by the model, resulting in incorrect answers, which we define as "Tool Ignored”. This indicates that the model does not know when to trust or ignore the tool. To overcome these limitations, We introduce Adaptive Tool Trust Calibration (ATTC), a novel framework that guides the model to adaptively choose to trust or ignore the tool results based on the confidence score of generated code blocks. The experimental results from various open-source TIR models of different sizes and across multiple
datasets demonstrate that ATTC effectively reduces the "Tool Ignored" issue, resulting in a performance increase of 4.1% to 7.5%.
Read the full abstract ▾
All authors Ruotao Xu, Yixin Ji, Yu Luo, Jinpeng Li, Dong Li, Peifeng Li, Juntao Li, Min Zhang
Computation and Language
Floating or Suggesting Ideas? A Large-Scale Contrastive Analysis of Metaphorical and Literal Verb-Object Constructions
Prisca Piccirilli, Alexander Fraser and Sabine Schulte im Walde
Metaphor pervades everyday
language, allowing speakers to express abstract concepts via concrete domains. While prior work has studied metaphors cognitively and psycholinguistically, large-scale comparisons with literal
language remain limited, especially for near-synonymous expressions. We analyze 297 English verb-object pairs (e.g., float idea vs. suggest idea) in ~2M corpus sentences, examining their contextual usage. Using five NLP tools, we extract 2,293 cognitive and linguistic features capturing affective, lexical, syntactic, and discourse-level properties. We address: (i) whether features differ between metaphorical and literal contexts (cross-pair analysis), and (ii) whether individual VO pairs diverge internally (within-pair analysis). Cross-pair results show literal contexts have higher lexical frequency, cohesion, and structural regularity, while metaphorical contexts show greater affective load, imageability, lexical diversity, and constructional specificity. Within-pair analyses reveal substantial heterogeneity, with most pairs showing non-uniform effects. These results suggest no single, consistent distributional pattern that distinguishes metaphorical from literal usage. Instead, differences are largely construction-specific. Overall, large-scale data combined with diverse features provides a fine-grained understanding of metaphor-literal contrasts in VO usage.
Read the full abstract ▾
Computation and Language
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
Jun Seo, Sangwon Ryu, Heejin Do et al. (+2 more)
Knowledge Tracing (KT) aims to predict learners' future performance from past interactions. While recent KT approaches have improved via learning item representations aligned with Knowledge Components, they overlook the procedural dynamics of problem solving. We propose Behavior-Aware Item Modeling (BAIM), a framework that enriches item representations by integrating dynamic procedural solution information. BAIM leverages a
reasoning language model to decompose each item's solution into four problem-solving stages (i.e., understand, plan, carry out, and look back), pedagogically grounded in Polya's framework. Specifically, it derives stage-level representations from per-stage
embedding trajectories, capturing latent signals beyond surface features. To reflect learner heterogeneity, BAIM adaptively routes these stage-wise representations, introducing a context-conditioned mechanism within a KT backbone, allowing different procedural stages to be emphasized for different learners. Experiments on XES3G5M and NIPS34 show that BAIM consistently outperforms strong pretraining-based baselines, achieving particularly large gains under repeated learner interactions.
Read the full abstract ▾
All authors Jun Seo, Sangwon Ryu, Heejin Do, Hyounghun Kim, Gary Geunbae Lee
Computation and Language
HyperMem: Hypergraph Memory for Long-Term Conversations
Juwei Yue, Chuanrui Hu, Jiawei Sheng et al. (+5 more)
Long-term
memory is essential for conversational
agents to maintain coherence, track persistent tasks, and provide personalized interactions across extended dialogues. However, existing approaches as
Retrieval-Augmented Generation (RAG) and graph-based
memory mostly rely on pairwise relations, which can hardly capture high-order associations, i.e., joint dependencies among multiple elements, causing fragmented
retrieval. To this end, we propose HyperMem, a hypergraph-based hierarchical
memory architecture that explicitly models such associations using hyperedges. Particularly, HyperMem structures
memory into three levels: topics, episodes, and facts, and groups related episodes and their facts via hyperedges, unifying scattered content into coherent units. Leveraging this structure, we design a hybrid lexical-semantic index and a coarse-to-fine
retrieval strategy, supporting accurate and efficient
retrieval of high-order associations. Experiments on the LoCoMo
benchmark show that HyperMem achieves state-of-the-art performance with 92.73% LLM-as-a-judge accuracy, demonstrating the effectiveness of HyperMem for long-term conversations.
Read the full abstract ▾
All authors Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo, Yafeng Deng
Computation and Language
Self-Debias: Self-correcting for Debiasing Large Language Models
Xuan Feng, Shuai Zhao, Luwei Xiao et al. (+2 more)
Although Large
Language Models (LLMs) demonstrate remarkable
reasoning capabilities, inherent social biases often cascade throughout the Chain-of-Thought (CoT) process, leading to continuous "Bias Propagation". Existing debiasing methods primarily focus on static constraints or external interventions, failing to identify and interrupt this propagation once triggered. To address this limitation, we introduce Self-Debias, a progressive framework designed to instill intrinsic self-correction capabilities. Specifically, we reformulate the debiasing process as a strategic resource redistribution problem, treating the model's output probability mass as a limited resource to be reallocated from biased heuristics to unbiased
reasoning paths. Unlike standard preference optimization which applies broad penalties, Self-Debias employs a fine-grained trajectory-level objective subject to dynamic debiasing constraints. This enables the model to selectively revise biased
reasoning suffixes while preserving valid contextual prefixes. Furthermore, we integrate an online self-improvement mechanism utilizing consistency filtering to autonomously synthesize supervision signals. With merely 20k annotated samples, Self-Debias activates efficient self-correction, achieving superior debiasing performance while preserving general
reasoning capabilities without continuous external oversight.
Read the full abstract ▾
All authors Xuan Feng, Shuai Zhao, Luwei Xiao, Tianlong Gu, Bo An
Computation and Language
Training Data Size Sensitivity in Unsupervised Rhyme Recognition
Petr Plecháč, Artjoms Šeļa, Silvie Cinková et al. (+7 more)
Rhyme is deceptively intuitive: what is or is not a rhyme is constructed historically, scholars struggle with rhyme classification, and people disagree on whether two words are rhymed or not. This complicates automated rhymed recognition and evaluation, especially in
multilingual context. This article investigates how much training data is needed for reliable unsupervised rhyme recognition using RhymeTagger, a
language-independent tool that identifies rhymes based on repeating patterns in poetry corpora. We evaluate its performance across seven
languages (Czech, German, English, French, Italian, Russian, and Slovene), examining how training size and
language differences affect accuracy. To set a realistic performance
benchmark, we assess inter-annotator agreement on a manually annotated subset of poems and analyze factors contributing to disagreement in expert annotations: phonetic similarity between rhyming words and their distance from each other in a poem. We also compare RhymeTagger to three large
language models using a one-shot learning strategy. Our findings show that, once provided with sufficient training data, RhymeTagger consistently outperforms human agreement, while LLMs lacking phonetic representation significantly struggle with the task.
Read the full abstract ▾
All authors Petr Plecháč, Artjoms Šeļa, Silvie Cinková, Mirella De Sisto, Lara Nugues, Neža Kočnik, Antonina Martynenko, Ben Nagy, Luca Giovannini, Robert Kolár
Computation and Language
Clickbait detection: quick inference with maximum impact
Soveatin Kuntur, Panggih Kusuma Ningrum, Anna Wróblewska et al. (+2 more)
We propose a lightweight hybrid approach to clickbait detection that combines OpenAI semantic
embeddings with six compact heuristic features capturing stylistic and informational cues. To improve efficiency,
embeddings are reduced using PCA and evaluated with XGBoost, GraphSAGE, and GCN classifiers. While the simplified feature design yields slightly lower F1-scores, graph-based models achieve competitive performance with substantially reduced inference time. High ROC–AUC values further indicate strong discrimination capability, supporting reliable detection of clickbait headlines under varying decision thresholds.
Read the full abstract ▾
All authors Soveatin Kuntur, Panggih Kusuma Ningrum, Anna Wróblewska, Maria Ganzha, Marcin Paprzycki
Computation and Language · Cross-listed from cs.LG
Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference
Baihui Liu, Kaiyuan Tian, Wei Wang et al. (+3 more)
Mixture-of-Experts (MoE) has become a dominant architecture for scaling large
language models due to their sparse activation mechanism. However, the substantial number of expert activations creates a critical latency bottleneck during inference, especially in resource-constrained deployment scenarios. Existing approaches that reduce expert activations potentially lead to severe model performance degradation. In this work, we introduce the concept of activation budget as a constraint on the number of expert activations and propose Alloc-MoE, a unified framework that optimizes budget allocation coordinately at both the layer and
token levels to minimize performance degradation. At the layer level, we introduce Alloc-L, which leverages sensitivity profiling and dynamic programming to determine the optimal allocation of expert activations across layers. At the
token level, we propose Alloc-T, which dynamically redistributes activations based on routing scores, optimizing budget allocation without increasing latency. Extensive experiments across multiple MoE models demonstrate that Alloc-MoE maintains model performance under a constrained activation budget. Especially, Alloc-MoE achieves $1.15\times$ prefill and $1.34\times$ decode speedups on DeepSeek-V2-Lite at half of the original budget.
Read the full abstract ▾
All authors Baihui Liu, Kaiyuan Tian, Wei Wang, Zhaoning Zhang, Linbo Qiao, Dongsheng Li
Computation and Language
Graph Neural Networks for Misinformation Detection: Performance-Efficiency Trade-offs
Soveatin Kuntur, Maciej Krzywda, Anna Wróblewska et al. (+4 more)
The rapid spread of online misinformation has led to increasingly complex detection models, including large
language models and hybrid architectures. However, their computational cost and deployment limitations raise concerns about practical applicability. In this work, we
benchmark graph neural networks (GNNs) against non-graph-based machine learning methods under controlled and comparable conditions. We evaluate lightweight GNN architectures (GCN, GraphSAGE, GAT, ChebNet) against Logistic Regression, Support Vector Machines, and Multilayer Perceptrons across seven public
datasets in English, Indonesian, and Polish. All models use identical TF-IDF features to isolate the impact of relational structure. Performance is measured using F1 score, with inference time reported to assess efficiency. GNNs consistently outperform non-graph baselines across all
datasets. For example, GraphSAGE achieves 96.8% F1 on Kaggle and 91.9% on WELFake, compared to 73.2% and 66.8% for MLP, respectively. On COVID-19, GraphSAGE reaches 90.5% F1 vs. 74.9%, while ChebNet attains 79.1% vs. 66.4% on FakeNewsNet. These gains are achieved with comparable or lower inference times. Overall, the results show that classic GNNs remain effective and efficient, challenging the need for increasingly complex architectures in misinformation detection.
Read the full abstract ▾
All authors Soveatin Kuntur, Maciej Krzywda, Anna Wróblewska, Marcin Paprzycki, Maria Ganzha, Szymon Łukasik, Amir H. Gandomi
Computation and Language
LLM-Based Data Generation and Clinical Skills Evaluation for Low-Resource French OSCEs
Tian Huang, Tom Bourgeade and Irina Illina
Objective Structured Clinical Examinations (OSCEs) are the standard method for assessing medical students' clinical and communication skills through structured patient interviews. In France, however, the organization of training sessions is limited by human and logistical constraints, restricting students' access to repeated practice and structured feedback. Recent advances in Natural
Language Processing (NLP) and Large
Language Models (LLMs) now offer the opportunity to automatically evaluate such medical interviews, thereby alleviating the need for human examiners during training. Yet, real French OSCE annotated transcripts remain extremely scarce, limiting reproducible research and reliable benchmarking. To address these challenges, we investigate the use of LLMs for both generating and evaluating French OSCE dialogues in a low-resource context. We introduce a controlled pipeline that produces synthetic doctor-patient interview transcripts guided by scenario-specific evaluation criteria, combining ideal and perturbed performances to simulate varying student skill levels. The resulting dialogues are automatically silver-labeled through an LLM-assisted framework supporting adjustable evaluation strictness. Benchmarking multiple open-source and proprietary LLMs shows that mid-size models ($\le$32B parameters) achieve accuracies comparable to GPT-4o ($\sim$90%) on synthetic data, highlighting the feasibility of locally deployable,
privacy-preserving evaluation systems for medical education.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
Small Vision-Language Models are Smart Compressors for Long Video Understanding
Junjie Fei, Jun Chen, Zechun Liu et al. (+13 more)
Adapting
Multimodal Large
Language Models (MLLMs) for hour-long
videos is bottlenecked by context limits. Dense visual streams saturate
token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse sampling or uniform pooling, blindly sacrifice fidelity by discarding decisive moments and wasting bandwidth on irrelevant backgrounds. We propose Tempo, an efficient query-aware framework compressing long
videos for downstream understanding. Tempo leverages a Small
Vision-
Language Model (SVLM) as a local temporal compressor, casting
token reduction as an early cross-modal
distillation process to generate compact, intent-aligned representations in a single forward pass. To enforce strict budgets without breaking causality, we introduce Adaptive
Token Allocation (ATA). Exploiting the SVLM's zero-shot relevance prior and semantic front-loading, ATA acts as a training-free $O(1)$ dynamic router. It allocates dense bandwidth to query-critical segments while compressing redundancies into minimal temporal anchors to maintain the global storyline. Extensive experiments show our 6B architecture achieves state-of-the-art performance with aggressive dynamic compression (0.5-16
tokens/frame). On the extreme-long LVBench (4101s), Tempo scores 52.3 under a strict 8K visual budget, outperforming GPT-4o and Gemini 1.5 Pro. Scaling to 2048 frames reaches 53.7. Crucially, Tempo compresses hour-long
videos substantially below theoretical limits, proving true long-form
video understanding relies on intent-driven efficiency rather than greedily padded context windows.
Read the full abstract ▾
All authors Junjie Fei, Jun Chen, Zechun Liu, Yunyang Xiong, Chong Zhou, Wei Wen, Junlin Han, Mingchen Zhuge, Saksham Suri, Qi Qian, Shuming Liu, Lemeng Wu, Raghuraman Krishnamoorthi, Vikas Chandra, Mohamed Elhoseiny, Chenchen Zhu
Computation and Language
Initialisation Determines the Basin: Efficient Codebook Optimisation for Extreme LLM Quantization
Ian W. Kennedy and Nafise Sadat Moosavi
Additive quantization enables extreme LLM compression with O(1) lookup-table dequantization, making it attractive for edge deployment. Yet at 2-bit precision, it often fails catastrophically, even with extensive search and finetuning. We show that the dominant bottleneck is codebook initialisation. Greedy sequential initialisation frequently places the model in poor optimisation regions that subsequent beam search and PV-tuning struggle to overcome. We analyse this behaviour through the representational ratio h̊o} = N/KM, which characterises the relationship between weight groups and codebook capacity, and propose OA-EM, an output-aware EM initialisation method using Hessian-weighted Mahalanobis distance. Across compression rates, search budgets, and three architectures (Llama 3.2 3B, Llama 3.1 8B, Qwen 2.5 3B), OA-EM consistently produces better solutions after PV-tuning and dominates the quality-compute frontier. The severity of the bottleneck scales with h̊o}: moderate at 3 bpp but extreme at 2 bpp, where poor initialisation can degrade perplexity by orders of magnitude. More broadly, our results highlight the importance of optimisation geometry in compressed model spaces, where initialisation can dominate subsequent search and fine-tuning.
Read the full abstract ▾
Computation and Language
Quantum Vision Theory Applied to Audio Classification for Deepfake Speech Detection
Khalid Zaman, Melike Sah, Anuwat Chaiwongyenc et al. (+1 more)
We propose
Quantum Vision (QV) theory as a new perspective for deep learning-based audio classification, applied to deepfake
speech detection. Inspired by particle-wave duality in
quantum physics, QV theory is based on the idea that data can be represented not only in its observable, collapsed form, but also as information waves. In conventional deep learning, models are trained directly on these collapsed representations, such as images. In QV theory, inputs are first transformed into information waves using a QV block, and then fed into deep learning models for classification. QV-based models improve performance in image classification compared to their non-QV counterparts. What if QV theory is applied
speech spectrograms for audio classification tasks? This is the motivation and novelty of the proposed approach. In this work, Short-Time
Fourier Transform (STFT), Mel-spectrograms, and Mel-Frequency Cepstral Coefficients (MFCC) of
speech signals are converted into information waves using the proposed QV block and used to train QV-based Convolutional Neural Networks (QV-CNN) and QV-based
Vision Transformers (QV-ViT). Extensive experiments are conducted on the ASVSpoof
dataset for deepfake
speech classification. The results show that QV-CNN and QV-ViT consistently outperform standard CNN and ViT models, achieving higher classification accuracy and improved robustness in distinguishing genuine and spoofed
speech. Moreover, the QV-CNN model using MFCC features achieves the best overall performance on the ASVspoof
dataset, with an accuracy of 94.20% and an EER of 9.04%, while the QV-CNN with Mel-spectrograms attains the highest accuracy of 94.57%. These findings demonstrate that QV theory is an effective and promising approach for audio deepfake detection and opens new directions for
quantum-inspired learning in audio perception tasks.
Read the full abstract ▾
All authors Khalid Zaman, Melike Sah, Anuwat Chaiwongyenc, Cem Direkoglu
Computation and Language
Dual-Pool Token-Budget Routing for Cost-Efficient and Reliable LLM Serving
Xunzhuo Liu, Bowei He, Xue Liu et al. (+3 more)
Production vLLM fleets typically provision each instance for the worst-case context length, leading to substantial KV-cache over-allocation and under-utilized concurrency. In practice, 80-95% of requests are short, yet are served under configurations optimized for long contexts, wasting 4-8$\times$ throughput capacity and triggering reliability issues such as OOM crashes, preemption, and request rejections. We identify a common root cause for these inefficiencies: configuration-traffic mismatch. We propose dual-pool
token-budget routing, a lightweight dispatch mechanism that partitions a homogeneous fleet into two specialized pools: a high-throughput short-context pool and a high-capacity long-context pool. Each request is routed based on its estimated total
token budget, computed using a per-category bytes-to-
token ratio that is learned online via exponential moving average from usage.
prompt_
tokens feedback, eliminating the need for a tokenizer. We also develop a simple analytical model that predicts fleet-level cost savings from workload characteristics and measured throughput differences, enabling practitioners to estimate benefits prior to deployment. Evaluations on real-world traces from the Azure LLM Inference
Dataset and LMSYS-Chat-1M, serving Llama-3-70B on A100 GPUs, show that our approach reduces GPU-hours by 31-42%, corresponding to \$2.86M annual savings at fleet scale, while lowering preemption rates by 5.4$\times$ and improving P99 TTFT by 6%. A case study with Qwen3-235B-A22B on AMD MI300X at 10,000 req/s projects \$15.4M in annual savings. The method incurs only O(1) dispatch overhead, adapts automatically to heterogeneous workloads, and composes seamlessly with existing optimizations such as PagedAttention, continuous batching, and prefill-decode disaggregation.
Read the full abstract ▾
All authors Xunzhuo Liu, Bowei He, Xue Liu, Andy Luo, Haichen Zhang, Huamin Chen
Computation and Language
Efficient Provably Secure Linguistic Steganography via Range Coding
Ruiyi Yan and Yugo Murawaki
Linguistic steganography involves
embedding secret messages within seemingly innocuous texts to enable covert communication. Provable security, which is a long-standing goal and key motivation, has been extended to
language-model-based steganography. Previous provably secure approaches have achieved perfect imperceptibility, measured by zero Kullback-Leibler (KL) divergence, but at the expense of
embedding capacity. In this paper, we attempt to directly use a classic
entropy coding method (range coding) to achieve secure steganography, and then propose an efficient and provably secure linguistic steganographic method with a rotation mechanism. Experiments across various
language models show that our method achieves around 100%
entropy utilization (
embedding efficiency) for
embedding capacity, outperforming the existing baseline methods. Moreover, it achieves high
embedding speeds (up to 1554.66 bits/s on GPT-2). The code is available at github.com/ryehr/RRC_steganography.
Read the full abstract ▾
Computation and Language
Guaranteeing Knowledge Integration with Joint Decoding for Retrieval-Augmented Generation
Zhengyi Zhao, Shubo Zhang, Zezhong Wang et al. (+7 more)
Retrieval-Augmented Generation (RAG) significantly enhances Large
Language Models (LLMs) by providing access to external knowledge. However, current research primarily focuses on
retrieval quality, often overlooking the critical ”integration bottleneck”: even when relevant documents are retrieved, LLMs frequently fail to utilize them effectively due to conflicts with their internal parametric knowledge. In this paper, we argue that implicitly resolving this conflict in a single generation pass is suboptimal. We introduce GuarantRAG, a framework that explicitly decouples
reasoning from evidence integration. First, we generate an ”Inner-Answer” based solely on parametric knowledge to capture the model's
reasoning flow. Second, to guarantee faithful evidence extraction, we generate a ”Refer-Answer” using a novel Contrastive DPO objective. This objective treats the parametric Inner-Answer as a negative constraint and the retrieved documents as positive ground truth, forcing the model to suppress internal
hallucinations in favor of external evidence during this phase. Finally, rather than naive concatenation or using the DPO trained model directly, we propose a joint decoding mechanism that dynamically fuses the logical coherence of the Inner-Answer with the factual precision of the Refer-Answer at the
token level. Experiments on five QA
benchmarks demonstrate that GuarantRAG improves accuracy by up to 12.1% and reduces
hallucinations by 16.3% compared to standard and dynamic RAG baselines.
Read the full abstract ▾
All authors Zhengyi Zhao, Shubo Zhang, Zezhong Wang, Yuxi Zhang, Huimin Wang, Yutian Zhao, Yefeng Zheng, Binyang Li, Kam-Fai Wong, Xian Wu
Computation and Language · Cross-listed from eess.AS
Rethinking Entropy Allocation in LLM-based ASR: Understanding the Dynamics between Speech Encoders and LLMs
Yuan Xie, Jiaqi Song, Guang Qiu et al. (+4 more)
Integrating large
language models (LLMs) into automatic
speech recognition (ASR) has become a dominant paradigm. Although recent LLM-based ASR models have shown promising performance on public
benchmarks, it remains challenging to balance recognition quality with latency and overhead, while
hallucinations further limit real-world deployment. In this study, we revisit LLM-based ASR from an
entropy allocation perspective and introduce three metrics to characterize how training paradigms allocate
entropy reduction between the
speech encoder and the LLM. To remedy
entropy-allocation inefficiencies in prevailing approaches, we propose a principled multi-stage training strategy grounded in capability-boundary awareness, optimizing parameter efficiency and
hallucination robustness. Specifically, we redesign the pretraining strategy to alleviate the
speech-text modality gap, and further introduce an iterative asynchronous SFT stage between
alignment and joint SFT to preserve functional decoupling and constrain encoder representation drift. Experiments on Mandarin and English
benchmarks show that our method achieves competitive performance with state-of-the-art models using only 2.3B parameters, while also effectively mitigating
hallucinations through our decoupling-oriented design.
Read the full abstract ▾
All authors Yuan Xie, Jiaqi Song, Guang Qiu, Xianliang Wang, Ming Lei, Jie Gao, Jie Wu
Computation and Language · Cross-listed from cs.AI
PASK: Toward Intent-Aware Proactive Agents with Long-Term Memory
Zhifei Xie, Zongzheng Hu, Fangda Ye et al. (+10 more)
Proactivity is a core expectation for AGI. Prior work remains largely confined to laboratory settings, leaving a clear gap in real-world proactive
agent: depth, complexity, ambiguity, precision and real-time constraints. We study this setting, where useful intervention requires inferring latent needs from ongoing context and grounding actions in evolving user
memory under latency and long-horizon constraints. We first propose DD-MM-PAS (Demand Detection,
Memory Modeling, Proactive
Agent System) as a general paradigm for streaming proactive AI
agent. We instantiate this paradigm in Pask, with streaming IntentFlow model for DD, a hybrid
memory (workspace, user, global) for long-term MM, PAS infra framework and introduce how these components form a closed loop. We also introduce LatentNeeds-Bench, a real-world
benchmark built from user-consented data and refined through thousands of rounds of human editing. Experiments show that IntentFlow matches leading Gemini3-Flash models under latency constraints, while identifying deeper user intent.
Read the full abstract ▾
All authors Zhifei Xie, Zongzheng Hu, Fangda Ye, Xin Zhang, Haobo Chai, Zihang Liu, Pengcheng Wu, Guibin Zhang, Yue Liao, Xiaobin Hu, Deheng Ye, Chunyan Miao, Shuicheng Yan
Computation and Language
Predicting the Benefit of Retrieval Augmentation in Open-Domain Question Answering
Or Dado, David Carmel and Oren Kurland
While
retrieval augmented generation has become a common approach for enhancing question answering systems,
retrieval is not universally advantageous. We study the problem of predicting whether incorporating external retrieved information is likely to improve response quality for a given question. To this end, we evaluate a range of prediction methods that are based on
retrieval signals, answer characteristics, and semantic consistency between generated responses and retrieved passages. We further devise a predictor that probes the LLM's internal state. Its prediction performance significantly narrows the performance gap between post-generation methods which are computationally demanding and pre-generation (post-
retrieval) methods. We use the prediction methods to devise a selective
retrieval framework that dynamically chooses between
retrieval and non-
retrieval generation modes per question. Experimental results demonstrate that selectively applying
retrieval augmentation yields answer quality that transcends that of using
retrieval for all queries.
Read the full abstract ▾
Computation and Language
A Decomposition Perspective to Long-context Reasoning for LLMs
Yanling Xiao, Huaibing Xie, Guoliang Zhao et al. (+8 more)
Long-context
reasoning is essential for complex real-world applications, yet remains a significant challenge for Large
Language Models (LLMs). Despite the rapid
evolution in long-context
reasoning, current research often overlooks the internal complexity of the long-context
reasoning task itself. In this paper, we move beyond this holistic view and decompose long-context
reasoning into a set of fundamental atomic skills, and we then automatically synthesize a suite of pseudo
datasets, each explicitly targeting a specific atomic skill. Our empirical analysis confirms that proficiency in these atomic skills is strongly correlated with general long-text
reasoning performance. Building on this insight, we employ reinforcement learning on these pseudo
datasets to sharpen the model's atomic skills, in the hope of boosting its general long-context
reasoning ability. Extensive experiments across multiple
benchmarks demonstrate the effectiveness of our approach: it outperforms a strong baseline by an average margin of 7.7% (improving from 46.3% to 54.0%) across Loogle, Loong, LongBench-v2, BrowscompLong, Ruler-qa2, and MRCR.
Read the full abstract ▾
All authors Yanling Xiao, Huaibing Xie, Guoliang Zhao, Shihan Dou, Shaolei Wang, Yiting Liu, Nantao Zheng, Cheng Zhang, Pluto Zhou, Zhisong Zhang, Lemao Liu
Computation and Language
Kathleen: Oscillator-Based Byte-Level Text Classification Without Tokenization or Attention
George Fountzoulas
We present Kathleen, a text classification architecture that operates directly on raw UTF-8 bytes using frequency-domain processing – requiring no tokenizer, no
attention mechanism, and under 470K parameters. Kathleen introduces several novel components: (1) RecurrentOscillatorBanks – damped sinusoid convolutions with temporal
memory for O(L) sequence processing; (2) an FFT-Rotate Wavetable Encoder that maps all 256 byte values using a single learnable vector (256 floats); (3) PhaseHarmonics – a sinusoidal non-linearity with just 6 learnable phase parameters (+2.6% accuracy, <0.001% of model parameters); (4) Content-Dependent Reverb with Positional Decay Modulation – a temporal
memory mechanism whose decay rate is jointly conditioned on input content and a learned position-indexed bias vector; (5)
Token-Level Module Sequencer with consonance and dissonance interference channels. Through iterative architecture
evolution from an initial 733K-parameter baseline (Kathleen-Clean) to the current Kathleen-V9 (469K parameters), we demonstrate that pretraining can be entirely eliminated while improving accuracy. Kathleen-V9 achieves 88.5% +/- 0.2% on IMDB, 92.4% +/- 0.2% on AG News, and 85.8% +/- 0.5% on SST-2 (3-seed averages) – matching or exceeding the pretrained baseline on all
benchmarks with 36% fewer parameters. On SST-2, the improvement is +2.5% absolute over the pretrained predecessor. Kathleen processes sequences in O(L) time and
memory.
Read the full abstract ▾
Computation and Language
AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification
Hongyi Cen, Mingxin Wang, Yule Liu et al. (+3 more)
Large
language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, weaken, or correct the false proposition they are supposed to preserve. We introduce AtomEval, a validity-aware evaluation protocol for fixed-evidence
adversarial claim rewriting. AtomEval represents claims as subject–relation–object–modifier (SROM) atoms, applies a one-way preservation gate to separate valid verifier evasion from proposition-changing rewrites, and reports validity-aware attack success rate (VASR), which counts only verifier-evasive rewrites that preserve the original false proposition. AtomEval further provides fine-grained diagnostics that explain both proposition-level failures and non-minimal valid rewrites. On FEVER refuted-claim rewriting, AtomEval exposes and explains ASR inflation: many apparent attacks fool the verifier by altering, weakening, or correcting the proposition they should preserve. By making attacked-proposition preservation explicit and measurable, AtomEval provides a stable evaluation target for evaluating
adversarial rewriters that must balance verifier evasion with proposition preservation.
Read the full abstract ▾
All authors Hongyi Cen, Mingxin Wang, Yule Liu, Jingyi Zheng, Hanze Jia, Tan Tang
Computation and Language
Rethinking Data Mixing from the Perspective of Large Language Models
Yuanjian Xu, Tianze Sun, Changwei Xu et al. (+7 more)
Data mixing strategy is essential for large
language model (LLM) training. Empirical evidence shows that inappropriate strategies can significantly reduce generalization. Although recent methods have improved empirical performance, several fundamental questions remain open: what constitutes a domain, whether human and model perceptions of domains are aligned, and how domain weighting influences generalization. We address these questions by establishing formal connections between gradient dynamics and domain distributions, offering a theoretical framework that clarifies the role of domains in training dynamics. Building on this analysis, we introduce DoGraph, a reweighting framework that formulates data scheduling as a graph-constrained optimization problem. Extensive experiments on GPT-2 models of varying scales demonstrate that DoGraph consistently achieves competitive performance.
Read the full abstract ▾
All authors Yuanjian Xu, Tianze Sun, Changwei Xu, XinLong Zhao, Jianing Hao, Ran Chen, Yang Liu, Ruijie Xu, Stephen Chen, Guang Zhang
Computation and Language · Cross-listed from cs.CV
TOOLCAD: Exploring Tool-Using Large Language Models in Text-to-CAD Generation with Reinforcement Learning
Yifei Gong, Xing Wu, Wenda Liu et al. (+1 more)
Computer-Aided Design (CAD) is an expert-level task that relies on long-horizon
reasoning and coherent modeling actions. Large
Language Models (LLMs) have shown remarkable advancements in enabling
language agents to tackle real-world tasks. Notably, there has been no investigation into how tool-using LLMs optimally interact with CAD engines, hindering the emergence of LLM-based agentic text-to-CAD modeling systems. We propose ToolCAD, a novel agentic CAD framework deploying LLMs as tool-using
agents for text-to-CAD generation. Furthermore, we introduce an interactive CAD modeling gym to rollout
reasoning and tool-augmented interaction trajectories with the CAD engine, incorporating hybrid feedback and human supervision. Meanwhile, an end-to-end post-training strategy is presented to enable the LLM
agent to elicit refined CAD Modeling Chain of Thought (CAD-CoT) and evolve into proficient CAD tool-using
agents via online curriculum reinforcement learning. Our findings demonstrate ToolCAD fills the gap in adopting and training open-source LLMs for CAD tool-using
agents, enabling them to perform comparably to proprietary models, paving the way for more accessible and robust autonomous text-to-CAD modeling systems.
Read the full abstract ▾
All authors Yifei Gong, Xing Wu, Wenda Liu, Kang Tu
Computation and Language
Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning
Shiwan Zhao, Zhihu Wang, Xuyang Zhao et al. (+10 more)
Post-training has become central to turning pretrained large
language models (LLMs) into aligned, capable, and deployable systems. Recent progress spans supervised fine-tuning (SFT), preference optimization, reinforcement learning (RL), process supervision, verifier-guided methods,
distillation, and multi-stage pipelines. Yet these methods are often discussed in fragmented ways, organized by labels or objectives rather than by the behavioral bottlenecks they address. This survey argues that LLM post-training is best understood as structured intervention on model behavior. We organize the field first by trajectory provenance, which defines two primary regimes: off-policy learning on externally supplied trajectories and on-policy learning on learner-generated rollouts. We then interpret methods through two recurring roles – effective support expansion, which makes useful behaviors more reachable, and policy reshaping, which improves behavior within already reachable regions – together with a complementary systems-level role, behavioral consolidation, which preserves, transfers, and amortizes useful behavior across stages and model transitions. Under this view, SFT may serve either support expansion or policy reshaping; preference optimization is usually off-policy reshaping, though online variants move closer to learner-generated states. On-policy RL often improves behavior on learner-generated states, but stronger guidance can also make hard-to-reach
reasoning paths reachable.
Distillation is often better understood as consolidation rather than only compression, and hybrid pipelines emerge as coordinated multi-stage compositions. Overall, the framework helps diagnose post-training bottlenecks and reason about stage composition, suggesting that progress increasingly depends on coordinated systems design rather than any single dominant objective.
Read the full abstract ▾
All authors Shiwan Zhao, Zhihu Wang, Xuyang Zhao, Jiaming Zhou, Caiyue Xu, Chenfei Liu, Liting Zhang, Yuhang Jia, Yanzhe Zhang, Hualong Yu, Zichen Xu, Qicheng Li, Yong Qin
Computation and Language
HCRE: LLM-based Hierarchical Classification for Cross-Document Relation Extraction with a Prediction-then-Verification Strategy
Guoqi Ma, Liang Zhang, Hongyao Tu et al. (+6 more)
Cross-document relation extraction (RE) aims to identify relations between the head and tail entities located in different documents. Existing approaches typically adopt the paradigm of “Small
Language Model (SLM) + Classifier”. However, the limited
language understanding ability of SLMs hinders further improvement of their performance. In this paper, we conduct a preliminary study to explore the performance of Large
Language Models (LLMs) in cross-document RE. Despite their extensive parameters, our findings indicate that LLMs do not consistently surpass existing SLMs. Further analysis suggests that the underperformance is largely attributed to the challenges posed by the numerous predefined relations. To overcome this issue, we propose an LLM-based \underline{H}ierarchical \underline{C}lassification model for cross-document \underline{RE} (HCRE), which consists of two core components: 1) an LLM for relation prediction and 2) a hierarchical relation tree derived from the predefined relation set. This tree enables the LLM to perform hierarchical classification, where the target relation is inferred level by level. Since the number of child nodes is much smaller than the size of the entire predefined relation set, the hierarchical relation tree significantly reduces the number of relation options that LLM needs to consider during inference. However, hierarchical classification introduces the risk of error propagation across levels. To mitigate this, we propose a prediction-then-verification inference strategy that improves prediction reliability through multi-view verification at each level. Extensive experiments show that HCRE outperforms existing baselines, validating its effectiveness.
Read the full abstract ▾
All authors Guoqi Ma, Liang Zhang, Hongyao Tu, Hao Fu, Hui Li, Yujie Lin, Longyue Wang, Weihua Luo, Jinsong Su
Computation and Language · Cross-listed from cs.AI
SAT: Balancing Reasoning Accuracy and Efficiency with Stepwise Adaptive Thinking
Weiyang Huang, Xuefeng Bai, Kehai Chen et al. (+4 more)
Large
Reasoning Models (LRMs) have revolutionized complex problem-solving, yet they exhibit a pervasive "overthinking", generating unnecessarily long
reasoning chains. While current solutions improve
token efficiency, they often sacrifice fine-grained control or risk disrupting the logical integrity of the
reasoning process. To address this, we introduce Stepwise Adaptive Thinking (SAT), a framework that performs step-level, difficulty-aware
pruning while preserving the core
reasoning structure. SAT formulates
reasoning as a Finite-State Machine (FSM) with distinct thinking modes (Slow, Normal, Fast, Skip). It navigates these states dynamically using a lightweight Process Reward Model (PRM), compressing easy steps while preserving depth for hard ones. Experiments across 9 LRMs and 7
benchmarks show that SAT achieves up to 40% reduction in
reasoning tokens while generally maintaining or improving accuracy.
Read the full abstract ▾
All authors Weiyang Huang, Xuefeng Bai, Kehai Chen, Xinyang Chen, Yibin Chen, Weili Guan, Min Zhang