Computation and Language · Cross-listed from cs.LG
Fork-Think with Confidence
Zena Al-Khalili, Rafi Hakim, Dietrich Klakow et al. (+1 more)
Parallel thinking has enjoyed great success for boosting LLM performance on
reasoning tasks without the need for any re-training. However, existing methods follow a think-first-then-decide paradigm, i.e., they first sample multiple
reasoning paths, which inevitably leads to overgeneration, then prune or stop unnecessary paths to compensate. In contrast, decide-first-then-think, i.e., first identifying points that are likely to lead to desirable generations, has been underexplored so far. Following this paradigm, we propose Fork-think with confidence, that first identifies forking points using model confidence in a single seeding path, then triggers thinking, sampling multiple continuations and aggregating them for the final response. Our experiments across three models and three
reasoning benchmarks show that Fork-think reduces the
token consumption by up to 30% and run-time by up to 57%, while performing comparable to or better than parallel thinking. Our analysis reveals that Fork-think is able to identify forking points that are meaningful with respect to the downstream task and that sampling at later positions can lead to substantially better generations. Finally, we demonstrate how combining Fork-think with existing mechanisms such as early stopping and weighted voting can further boost the performance and perform comparably to existing state-of-the-art methods, without requiring any warm-up or offline training. Our results establish pre-determined forking as a promising research direction for efficient LLM
reasoning.
Read the full abstract ▾
All authors Zena Al-Khalili, Rafi Hakim, Dietrich Klakow, Ji-Ung Lee
Computation and Language
Team MKC at CLPsych 2026: Capturing and Characterizing Mental Health Changes through Social Media Timeline Dynamics
Kyomin Hwang, Hyeonjin Kim, Hyunho Lee et al. (+1 more)
Recent advances in Large
Language Models (LLMs) have motivated their adoption across a wide range of domains, including Artificial Intelligence (AI) for mental health. Given the growing prevalence of mental health disorders worldwide and the limited accessibility of professional care, there is an increasing demand for scalable computational approaches that can assist in early detection and continuous monitoring of psychological well-being. In this area, ongoing efforts have focused on curating domain-specific
datasets and leveraging them to develop LLMs capable of supporting holistic mental health analysis. In line with this direction, we propose an LLM-based pipeline for comprehensive mental health analysis over sequentially ordered user posts, as part of the CLPsych shared task. Our pipeline offers a unified framework that jointly enables post-level assessment and user-level temporal modeling.
Read the full abstract ▾
All authors Kyomin Hwang, Hyeonjin Kim, Hyunho Lee, Nojun Kwak
Computation and Language
Revising RVL-CDIP: Quantifying Errors and Test-Train Overlap
Stefan Larson, Attila Nagy, Sam Desai et al. (+8 more)
RVL-CDIP is a popular
dataset for benchmarking document classifiers. However, the
dataset contains ample amounts of label errors as well as non-trivial amounts of test-train overlap, both of which may impact model performance metrics. In this paper, we address these two problems by (1) finding and fixing label errors, and (2) detecting and addressing test-train overlap. We produce several variations of RVL-CDIP with label error and test-train overlap fixes, and
benchmark document classification performance on these new RVL-CDIP variations. Our rigorous analysis of RVL-CDIP finds that the corpus contains 12% label error and approximately 35% test-train duplication. Remediation sees improvements in classification accuracy when errors are removed, but sees decreases in accuracy when duplicates are removed. We additionally evaluate models on RVL-CDIP-N, an out-of-distribution
benchmark, finding that training on error-corrected data substantially improves OOD generalization, with supervised models gaining an average of 8.1 percentage points in accuracy and improvements as large as 14 percentage points.
Read the full abstract ▾
All authors Stefan Larson, Attila Nagy, Sam Desai, Cyrus Desai, Nicole C. Lima, Yixin Yuan, Siddharth Betala, Kaushal K. Prajapati, Jamiu T. Suleiman, Sharad Duwal, Kevin Leach
Computation and Language · Cross-listed from cs.AI
CDR-Bench: Evaluating Faithful Execution of Compositional, Order-Sensitive Data Refinement Recipes
Yuchen Huang, Xiang Li, Zhenqing Ling et al. (+5 more)
Data refinement involves executing multi-step recipes over evolving text states, where both composition and execution order of processing operators determine the outcome. While existing
benchmarks either isolate text editing or entangle it with code and tool execution, it remains unclear whether LLMs can directly and faithfully execute these compositional, order-sensitive data refinement recipes. To fill this gap, we introduce CDR-Bench, a comprehensive
benchmark featuring 3,462 high-quality tasks spanning four real-world data refinement domains and 29 distinct operators. Our
benchmark evaluates models across atomic, order-agnostic, and order-sensitive settings, leveraging deterministic reference outputs to enable exact evaluation. Experiments on 10+ state-of-the-art LLMs reveal consistent failure patterns: performance degrades sharply in compositional settings, and order-sensitive recipe success collapses. These findings underline that current LLMs lack the procedural faithfulness required for reliable compositional data refinement.
Read the full abstract ▾
All authors Yuchen Huang, Xiang Li, Zhenqing Ling, Sijia Li, Qianli Shen, Daoyuan Chen, Yi R. Fung, Yaliang Li
Computation and Language
Clinically Structured Rank-Gated LoRA for Cross-Benchmark Medical Question Answering
Hao Gong, Ruilin Gong and Yining Huang
Medical multiple-choice question answering requires parameter-efficient adaptation across heterogeneous knowledge domains and
reasoning operations. A medication question, a diagnostic decision, a public-health item, and a nursing-action item may require different low-rank updates, while some recall items should preserve the base model's representation with only mild adapter intervention. We propose BiRG-LoRA, a single-adapter rank-gated LoRA method for medical question answering. BiRG-LoRA keeps one LoRA module per target layer but makes its rank dimension input-conditioned: for each question, a biaxial gate combines hidden semantic evidence with specialty/profession priors, clinical-operation priors, and their interaction to select a sparse top-$k$ subset of rank atoms. A scalar injection coefficient further controls the strength of the selected adapter update. Under a matched Qwen3-8B CMB-source protocol, BiRG-LoRA achieves the highest four-
benchmark macro-average accuracy among trainable PEFT baselines and matched routing controls: 69.31% averaged over CMB, CMExam, MedQA, and MedMCQA. It improves over MoELoRA by 0.89 percentage points while using 28.1% fewer trainable parameters; a paired,
benchmark-stratified bootstrap over final predictions gives a 95% confidence interval of [0.42, 1.37] for this macro-average gain. Basic controls show that BiRG-LoRA also improves over vanilla LoRA r16 and active-rank-matched LoRA r4 by 0.83 macro points, and an evaluation-time weak-axis perturbation check suggests that performance is not brittle to moderate tag noise. The results support a bounded claim: clinically structured rank allocation improves cross-
benchmark medical QA under a matched single-seed protocol, while training-seed variance remains future work.
Read the full abstract ▾
Computation and Language
Linguistic Bias Mitigation for Spoofing Detection via Gradient Reversal and A Variational Information Bottleneck
Anh-Tuan Dao, Driss Matrouf, Mickael Rouvier et al. (+1 more)
Rapid advancements in generative
speech technology have compromised the reliability of voice biometrics. While current spoofing detectors excel when assessed under in-domain conditions, generalisation to out-of-domain settings is often poor. We show that this can be due to linguistic bias. A reliance on linguistic cues observed in training data can then compromise robustness to cross-data. We propose a linguistic-invariant spoofing detection framework utilizing teacher-student
adversarial learning. The linguistic-aware teacher model, pre-trained on linguistic content of an external
dataset, guides the student detector via gradient reversal to minimize the linguistic information. To prevent the inadvertent removal of non-linguistic cues, we incorporate a Variational Information Bottleneck to enable suppression of principal cues. Across nine DF Arena
datasets, our method achieves up to a 36.2% relative reduction in the EER compare to the baseline.
Read the full abstract ▾
All authors Anh-Tuan Dao, Driss Matrouf, Mickael Rouvier, Nicholas Evans
Computation and Language · Cross-listed from cs.CV
Visual Semantic Entropy: Do Vision Language Models Recognize Visual Ambiguity?
Ta Duc Huy, Trang Nguyen, Townim Chowdhury et al. (+5 more)
Vision-
language models can produce confident answers on visually ambiguous inputs, resulting in biased predictions. Common
entropy-based methods, such as Semantic
Entropy (SE), rely on output diversity. Yet our analysis shows that overconfident visual
embeddings suppress output diversity under
stochastic decoding, causing SE to underestimate uncertainty in such cases. Recent methods instead probe output diversity through input perturbations, including textual paraphrasing or joint text-image perturbations, and show improved performance. We study these approaches and reveals that the resulting variability is often dominated by textual changes rather than visual evidence, causing uncertainty estimates to reflect
prompt sensitivity rather than visual ambiguity. We therefore propose Visual Semantic
Entropy (VSE), which perturbs only the image to probe nearby visual variations while keeping the text query fixed. VSE measures uncertainty by clustering generated answers into semantic prototypes and computing the mass-weighted dispersion among them. Extensive evaluation across five modern
vision-
language models and five diverse VQA
benchmarks demonstrates that VSE effectively captures visual ambiguity, establishing a new state-of-the-art for VLM uncertainty estimation.
Read the full abstract ▾
All authors Ta Duc Huy, Trang Nguyen, Townim Chowdhury, Ankit Yadav, Minh-Son To, Zhibin Liao, Johan W. Verjans, Vu Minh Hieu Phan
Computation and Language · Cross-listed from cs.LG
Calibrating the Evaluator: Does Probability Calibration Mitigate Preference Coupling in LLM Agent Feedback Loops?
Zewen Liu
When large
language model (LLM)
agents adapt their behavior through evaluator feedback, systematic evaluator biases propagate into the
agent's learned strategy distribution - a phenomenon termed evaluator preference coupling. Prior work has documented this coupling and established a diagnostic framework (EPC) to measure it, but has not investigated whether calibration techniques can mitigate the effect. We present the first study of evaluator calibration as mitigation: applying probability calibration to the evaluator's pairwise judgments to reduce spurious preference propagation. In a controlled within-subjects experiment (N=5) comparing standard binary TTRL (win/loss) with confidence-calibrated TTRL (probability-weighted updates) using DeepSeek-V4-Pro as executor and GLM5.2 as evaluator, we find that calibration reduces the coupling coefficient gamma by 20-49% and Jensen-Shannon divergence by 45-67%. A symmetric-LR control confirms the effect is not due to reduced update asymmetry. We release the calibrated TTRL protocol and recommend it as a lightweight mitigation for LLM-as-judge deployment pipelines.
Read the full abstract ▾
Computation and Language
BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Hao Zhang, Yiming Hu, Yong Wang et al. (+3 more)
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate
tokens in parallel, and are then verified by the target model, enabling lossless acceleration. Recently,
diffusion-based speculative decoding further improves parallelism by generating multiple
tokens per forward pass via block-level
diffusion, achieving state-of-the-art (SOTA) performance. However, existing methods adopt a fixed inference block size and assume a uniform optimal decoding strategy across all inputs. In this paper, we show that this assumption is suboptimal, as the optimal block size varies across samples and plays a critical role in speculative decoding performance. Moreover, these values exhibit a clear local structure, concentrating around the training block size, which reduces the problem to a low-dimensional and structured decision space. Based on these insights, we propose BlockPilot, a sample-adaptive policy that predicts the optimal block size from the prefilling representation. Specifically, we formulate block size selection as a lightweight policy learning problem and propose an instance-adaptive decision mechanism that predicts the optimal block size based on the representation of the prefilling stage. The prediction is performed only once after prefilling, allowing for seamless integration. Extensive experiments demonstrate that our method is plug-and-play, introduces minimal overhead, and consistently improves efficiency, achieving an acceptance length of 5.92 and a 4.20$\times$ speedup on Qwen3-4B under temperature $T=1$.
Read the full abstract ▾
All authors Hao Zhang, Yiming Hu, Yong Wang, Mingqiao Mo, Xin Xiao, Xiangxiang Chu
Computation and Language
LOPA: Enhancing Spoken Language Assessment via Latent Ordinal Prototype Alignment
Hong-Yun Lin, Fu-An Chao, Bi-Cheng Yan et al. (+1 more)
Fueled by increasing model scale and
multimodal inputs,
Multimodal Large
Language Models (MLLMs) have emerged as a promising paradigm for Spoken
Language Assessment (SLA). While effective, this paradigm often overlooks the intrinsic ordinal structure of
language acquisition. This paper works around the necessity of large-scale MLLMs by introducing Latent Ordinal Prototype
Alignment (LOPA) for SLA, a prototype-based regularizer that enforces an ordinal
geometric prior directly on the latent space. Coupled with Semantic-Anchored Layer Routing (SALR), which adaptively harvests multi-depth representations from a frozen Whisper encoder, our framework achieves an RMSE of 0.361. This performance rivals billion-parameter systems without the need for LLM-based fine-tuning. Further analysis reveals that SALR's synergy with LOPA offers interpretable, criterion-aligned preferences, thereby supporting an efficient and ordinal-aware modeling alternative to current scaling-centric models for SLA.
Read the full abstract ▾
All authors Hong-Yun Lin, Fu-An Chao, Bi-Cheng Yan, Berlin Chen
Computation and Language
When the Database Fails: Prompting LLM Dialogue Agents for Safe Recovery in Task-Oriented Dialogue
Mohammad Alijanpour Shalmani, Alale Rezvani Boroujeni and Jiann Shiun Yuan
Large
language models used in task-oriented dialogue often produce fluent but unsafe responses when backend database calls fail, return empty results, or surface mismatched information, inventing venues, confirmations, or booking details not grounded in the database. We study a lightweight prompting-based recovery approach that improves robustness without retraining or additional model calls. We compare three response strategies, including a guided recovery
prompt conditioned on structured database status, across six open-weight model families (DeepSeek-R1, Gemma-2, Llama-3, Mistral, Phi-3, and Qwen-2.5) and four database conditions: empty result, wrong-domain
retrieval, API error, and clean
retrieval. Using fault-injected
benchmarks built on two structurally different
datasets, MultiWOZ 2.2 (5 domains) and SGD (20 domains), we find that naive
agents hallucinate on 30.5% of failure turns on MultiWOZ and 20.9% on SGD. Our Guided-Retry strategy reduces
hallucination by 50% on MultiWOZ (30.5 to 15.3%) and by 42% on SGD (20.9 to 12.2%) without retraining. However, residual
hallucination remains substantial (6-37% across models), with wrong-domain failures the hardest case. Results are consistent across both
datasets and all six model families, and human annotation shows substantial agreement while supporting the validity of the automatic commitment-safety metric.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CR
The Decomposition Is the Fingerprint: Per-Component Identity for Agent Skills
Hongliang Liu, Yuhao Wu and Tung-Ling Li
AI
agents increasingly acquire and execute skills at runtime: bundles of
prompt instructions, executable code, and tool declarations fetched from marketplaces and other
agents. Governing them needs a stable notion of skill identity, yet cryptographic hashing is engineered to destroy the very similarity we need, as a one-character edit scrambles the digest. We present a compact, locality-sensitive fingerprint that embeds each component of a skill and projects it to bits with a multi-bank SimHash, giving a fixed 120-byte signature compared in constant time by Hamming distance. Our central claim is that keeping the fingerprint as a per-component triple (
prompt, code, tools), rather than a single score, is what makes it useful: the triple recovers skill-family identity through paraphrase, renaming, refactoring, and controlled code translation when another component remains shared, while independent
multilingual reimplementation is not recovered; it also localizes which component carries the reuse. We claim lineage, not behavioral equivalence: identity supplies the structural axis of a registry and leaves safety to behavioral verification. The fingerprint reaches an area under the ROC curve (AUC) of 0.974 (95% CI [0.956, 0.994]) over 4,950 pairwise comparisons while using 77x fewer bits than the
embedding it approximates, with ranking preserved in expectation and finite-bit concentration; the per-component split turns one number into relationship classification, families, novelty, and a portable "SkillBOM" for a skill registry. On a 906-skill injection
benchmark the fingerprint recognizes injected skills as tampered copies of a known base and localizes the change, but recognition is not trust: it remains, by design, an identity signal complementary to behavioral verification rather than a safety verdict.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
Learning from Failure: Inference-Time Self-Improvement for Computer-Use Agents
Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt et al. (+2 more)
Computer-use
agents, which leverage
multimodal large
language models (MLLMs) to operate computers and complete tasks, have attracted significant
attention for their utility and versatility. A major challenge in developing these
agents is collecting large-scale, high-quality trajectories. The standard approach generates synthetic data through a self-improving loop: an
agent is placed in a verifiable environment and iteratively fine-tuned on its successful trajectories. Despite its effectiveness, this paradigm exploits only successful trajectories and discards the failed ones, even though failures carry rich information about a model's weaknesses. In this work, we explore a complementary failure-driven self-improvement loop, a data-centric paradigm that turns failed trajectories into
agent improvements. Specifically, we employ an LLM to diagnose failure modes, propose inference-time solutions, and generate code patches – lightly verified by humans – that upgrade the
agent. We validate this approach with the state-of-the-art OpenCUA-72B model on the OSWorld
benchmark, improving the success rate from 42.3% to 48.9%, a gain of 6.6 percentage points, without any additional training cost and with only modest inference overhead. Our results demonstrate that failure-driven self-improvement is a viable complement to success-based pipelines, enabling more efficient
agent improvement.
Read the full abstract ▾
All authors Xueqiao Sun, Xiaohan Wang, Ludwig Schmidt, Serena Yeung-Levy, Yuhui Zhang
Computation and Language
Probing Stylistic Appropriation using Large Language Models: An Evaluation Framework for Copyright Infringement under EU Law
Noah Scharrenberg and Chang Sun
Large
language models (LLM) trained on web-scale corpora generate output that may infringe copyright, yet existing technical safeguards focus narrowly on verbatim memorisation. EU copyright doctrine applies a broader standards: substantial similarity, which extends to stylistic choices, narrative structure, and creative elaboration. This mismatch between what current methods detect and what the law protects leaves a significant compliance gap. We introduce PSALM, an LLM-as-a-judge framework that operationalises EU copyright doctrine through ten evaluators assessing computational overlap, stylistic dimensions (writing style, narrative voice), content dimensions (character, plot, scene, world building), and statutory exceptions (parody, pastiche, quotation, scènes à faire). Applying PSALM to Llama~3.2 models fine-tuned on translated historical Dutch literary works, we find that: 1) instruction-tuned models exhibit non-trivial baseline stylistic similarity prior to corpus exposure; 2) fine-tuning induces systematic stylistic appropriation across all infringement-relevant dimensions, extending beyond verbatim memorisation to abstract narrative patterns; 3) Negative Preference Optimisation unlearning substantially reduces similarity but leaves detectable residual stylistic patterns. These findings indicate that safeguards targeting literal copying alone are insufficient to mitigate broader copyright risks. PSALM provides infrastructure for auditable, legally informed compliance evaluation, though the relationship between automated similarity scores and infringement determinations requires validation by legal experts. This work bridges qualitative legal standards and quantitative technical measurement, exposing fundamental tensions between generative AI and EU intellectual property law.
Read the full abstract ▾
Computation and Language
Can LLMs Imagine Moral Alternatives Beyond Binary Dilemmas?
Jongchan Choi, Nari Yang, Sung Soo Park et al. (+4 more)
As LLMs increasingly serve as moral advisors and
agents, they must address conflicts between competing values. Yet prior work on moral dilemmas overlooks a central aspect of human moral cognition: imagining alternatives beyond the given options. We introduce MoralAltDataset, comprising 307 Advisor and AI-facing
Agent dilemmas augmented with compromise and reframed alternatives. We compare human and LLM judgments in binary and four-option settings. Across human participants and 15 LLMs, aggregate moral choice distributions differ substantially between the two settings, with compromise often preferred over either original binary option. Results show value shifts and stronger human-LLM agreement on alternatives. Source-stratified results reveal a descriptive gap: human alternative-selection rates are similar across authoring sources, whereas LLMs select GPT-5-authored alternatives substantially more often. We then compare human-authored alternatives with outputs from three representative LLMs through pairwise preference and expert-based evaluations. Alternatives from these LLMs are generally preferred and better satisfy fine-grained structural and ethical criteria, while revealing a trade-off between structural quality and practical feasibility. Our
dataset is available here: https://huggingface.co/
datasets/jongchanch/MoralAltDataset, and our project page is here: https://jongchanchoi.com/moral-imagination
Read the full abstract ▾
All authors Jongchan Choi, Nari Yang, Sung Soo Park, Jaemin Cho, Han Seoyoung, Haerin Shin, Jun-Hyung Park
Computation and Language
Gated Multi-Graph Fusion via Graph Attention Networks for Alzheimer's Disease Detection
Jinyu Li, Xiao Wei, Bin Wen et al. (+5 more)
Spontaneous
speech is a vital non-invasive biomarker for Alzheimer's Disease (AD), yet many systems overlook non-linear structural disruptions and clinical heterogeneity in pathological
language. We propose a Multi-View Gated Graph
Attention Network that transcribes audio via Automatic
Speech Recognition (ASR) to construct semantic, dependency, and co-occurrence graphs, characterizing
speech through a "content-structure-flow" framework. Notably, the co-occurrence graph leverages Pointwise Mutual Information (PMI) from a normative corpus to quantify narrative logic and linguistic deviation. To address symptomatic diversity, an adaptive gated fusion mechanism dynamically integrates these views. Evaluated on the ADReSSo
dataset, our model achieves 90.00% accuracy. Ablation results confirm that the PMI-based graph and heterogeneity-aware gating are essential for robust classification across diverse clinical populations. Our source code is publicly available at https://github.com/opeacc/AD.
Read the full abstract ▾
All authors Jinyu Li, Xiao Wei, Bin Wen, Kai Li, Yuqin Lin, Xiaobao Wang, Longbiao Wang, Jianwu Dang
Computation and Language · Cross-listed from cs.AI
HealthAgentBench: A Unified Benchmark Suite of Realistic Agentic Healthcare Environments for Challenging Frontier AI Agents
Qianchu Liu, Sheng Zhang, Guanghui Qin et al. (+18 more)
As AI
agents become increasingly capable of complex, long-horizon
reasoning, rigorous evaluation is essential for measuring progress toward real-world healthcare applications. However, existing healthcare
benchmarks are often static or narrow in clinical scope, motivating broader evaluation of
agents acting on raw patient data. We introduce HealthAgentBench, a suite of 75 agentic healthcare tasks across 9 categories each with its unique environment. The
benchmark suite spans diagnosis, specimen assessment, research, and data management workflows and a broad range of modalities. Each task is designed to replicate an end-to-end clinical workflow: given task instructions and supporting resources, an
agent must explore raw healthcare data, operate within a complex environment, and execute multi-step solutions that go beyond naive prompting, such as querying large clinical databases or interpreting gigapixel pathology images. All tasks are scored using binary success criteria derived from reference labels, executable rules, or computational baselines. We evaluate six
agents (three GPT models through Codex and three Claude models through Claude Code) with one scored attempt per task (450 evaluations). Overall success ranges from 32.0% to 57.3%; Claude Code Opus-5.5 leads with a 57.3% success rate, followed by GPT-6-astra and Sonnet-5.5 at 50.7% each. Performance varies substantially by category with specialized imaging modalities such as CT and MRI being especially difficult. HealthAgentBench provides a challenging and realistic
benchmark with substantial room for future progress. We release our
benchmark athttps://github.com/microsoft/HealthAgentBench.
Read the full abstract ▾
All authors Qianchu Liu, Sheng Zhang, Guanghui Qin, Jeya Maria Jose Valanarasu, Xiaoke Huang, Peniel Argaw, Maximilian Rokuss, Mingyu Lu, Timothy Ossowski, Juan Manuel Zambrano Chaves, Cliff Wong, Naisargi Patel, Yashna Hasija, Mu Wei, Wen-wai Yim, Qin Liu, Zilin Jing, Jason Entenmann, Naoto Usuyama, Tristan Naumann, Hoifung Poon
Computation and Language
TAG-DLM: Diffusion Language Models for Text-Attributed Graph Learning
Lingjie Chen, Yuanchen Bei, Haobo Xu et al. (+3 more)
Text-attributed graphs (TAGs), where each node carries a natural
language description, require models to jointly reason over text and graph
topology. Existing approaches often handle the two modalities separately: graph neural networks operate on shallow text features, while hybrids of LLMs and graphs use the
language model mainly as a text encoder and delegate structure learning to a separate graph module. We propose method that unifies textual
reasoning and graph message passing within a masked
diffusion language model, a
language model with bidirectional
attention and generative decoding. For each graph instance, method linearises a sampled local neighbourhood into a
token sequence and injects graph structure through a
topology attention mask, which realises message passing over the graph. Because the
diffusion language model can both interpret and generate text, the method adapts to different tasks simply by changing the
prompt, supporting node classification, link prediction, and cross-
dataset transfer with no target-specific fine-tuning. Experiments show that method outperforms graph neural networks, graph
transformers, and LLM-based baselines on all three TAG
benchmarks across two tasks, improving over the strongest baseline by up to 3.9 points.
Read the full abstract ▾
All authors Lingjie Chen, Yuanchen Bei, Haobo Xu, Yanjun Zhao, Yuzhong Chen, Hanghang Tong
Computation and Language · Cross-listed from cs.LG
ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries
Abhishek Dey
Large
language models deployed in regulated industries operate under two constraints: compliance enforcement and cost efficiency. Personally identifiable information (PII) in user queries can reach model endpoints before the system determines whether that data should leave its jurisdictional boundary. Serving all queries through a single large model consumes full GPU capacity regardless of query complexity while offering no mechanism for geographic routing. Mixture-of-Experts architectures do not address this routing occurs between expert layers within the model after data has already arrived at the endpoint, with all experts loaded in
memory regardless of query complexity. We propose a classifier-gated routing architecture that enforces compliance by design. A trained encoder classifier sits before any decoder inference, evaluating each query for complexity and data sensitivity, then routing it to an appropriately sized dense model in the appropriate geographic location. PII-containing queries route to local endpoints before any LLM computation begins, making data residency violations structurally impossible. Simple queries reach small, fast models at a fraction of the cost. Our evaluation on 600 queries demonstrates 39% median latency reduction, 33-52% cost savings depending on query distribution, and generation throughput of 122-200
tokens/second versus 50-64 for the baseline. The encoder classifier achieves 99.2% accuracy with near-perfect PII recall at 7ms inference overhead, establishing pre-inference classification as a practical path to compliance-by-design LLM deployment.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.CV
PruneGround: Plug-and-play Spatial Pruning for 3D Visual Grounding
Duc Cao Dinh, Khai Le-Duc, Florent Draye et al. (+4 more)
3D Visual Grounding (3DVG) aims to localize target objects in 3D scenes given natural
language descriptions. Existing approaches typically perform
reasoning over the entire scene, leading to ambiguous predictions and high computational cost, especially in cluttered environments. We observe that many referential expressions rely on local spatial context and often correspond to restricted spatial regions rather than the full scene. Motivated by this insight, we propose PruneGround, an effective plug-and-play framework for 3DVG built upon three key components. First, we introduce
Language-Guided Spatial
Pruning (LGSP), which leverages a frozen
Vision Language Model (VLM) to identify
language-relevant regions, thereby reducing spatial computation and grounding candidates in the narrower search space. Second, we propose MultiView-Conditioned Description Reformulation (MCDR), which decomposes complex expressions into simplified target–anchor relations and augments missing spatial cues through multi-view
reasoning. Finally, we propose LLM-Grounder, which repurposes a detection-pretrained spatial LLM into a
language-conditioned grounding model by aligning point cloud and linguistic representations within the pruned region. Extensive experiments on the three most popular point cloud
benchmarks demonstrate that our method achieves state-of-the-art results on all three ScanRefer settings and on 9 out of 10 Nr3D/Sr3D settings. Code and models are publicly available: https://github.com/leduckhai/PruneGround
Read the full abstract ▾
All authors Duc Cao Dinh, Khai Le-Duc, Florent Draye, Chris Ngo, Terry Jingchen Zhang, Bernhard Schölkopf, Zhijing Jin
Computation and Language
SeKV: Resolution-Adaptive KV Cache with Hierarchical Semantic Memory for Long-Context LLM Inference
Amirhossein Abaskohi, Giuseppe Carenini, Peter West et al. (+1 more)
Large
language models increasingly operate over long contexts, where the KV cache becomes a dominant
memory bottleneck: its size grows linearly with sequence length and must be retained throughout decoding, making full GPU caching prohibitively expensive without compression. Existing KV cache compression methods struggle to balance efficiency with faithful context preservation.
Token eviction discards information, while semantic grouping fixes compression decisions at prefill time; neither can recover
token-level detail from a compressed span once it becomes relevant during generation. As a solution, we propose SeKV, a resolution-adaptive semantic KV cache that organizes context into
entropy-guided semantic spans and stores them across a GPU-CPU
memory hierarchy without discarding information. Each span keeps a lightweight summary vector on GPU for coarse routing and a low-rank SVD basis on CPU for on-demand
token-level reconstruction. A trained zoom-in mechanism selectively expands query-relevant spans during decoding, enabling precise
retrieval without materializing the full KV cache on GPU. SeKV enables adaptive
token-level reconstruction while keeping the base LLM fully frozen and adding fewer than 0.05% trainable parameters. Across four
benchmarks, SeKV improves over the strongest semantic compression baseline by 5.9% on average while reducing GPU
memory by 53.3% versus full KV caching at 128K context. Code is available on https://github.com/AmirAbaskohi/SeKV.
Read the full abstract ▾
All authors Amirhossein Abaskohi, Giuseppe Carenini, Peter West, Yuhang He
Computation and Language · Cross-listed from cs.SD
UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling
Chuanbo Zhu, Wuyou Zhou, Rongxiu Zhong et al. (+4 more)
Speech editing aims to modify specific portions of an utterance while preserving the remaining
speech. Existing approaches primarily focus on word-level content modification and typically treat content, speaker, and
emotion editing as separate tasks, limiting both editing granularity and flexibility. We propose UniSAE, a unified
speech attribute editing framework which supports composable speaker,
emotion and content editing from sub-phoneme to word level within a single architecture. UniSAE introduces a Discrete Phonetic PosteriorGram (DPPG) representation that factorizes
speech content into discrete
tokens encoding phoneme identity, pronunciation variants, and duration, enabling direct phoneme- and sub-phoneme-level editing. For higher-level modifications, an autoregressive content
transformer predicts edited DPPG sequences for word-level content editing. The edited sequences are rendered into
speech by a
diffusion-based acoustic decoder, conditioned on disentangled speaker and
emotion representations. Experimental results demonstrate that the proposed unified framework supports precise speaker and
emotion control, content editing at multiple granularities, and joint modification of all three attributes within a single framework.
Read the full abstract ▾
All authors Chuanbo Zhu, Wuyou Zhou, Rongxiu Zhong, Shilei Zhang, Kun Qian, Yike Guo, Wei Xue
Computation and Language
What Counts as an Error? Dual-Reference Benchmarking for Atypical ASR
Hawau Olamide Toyin, Srinivasan Umesh and Hanan Aldarmaki
ASR systems have been often reported to underperform on atypical
speech. An often conflated compounding factor is the existence of two valid transcription references: verbatim (actual produced
speech, including repetitions/prolongations) and intended (the canonical form of the text with disfluencies removed) in atypical
speech recognition depending on context and use-case. Most ASR evaluations conflate this duality into a single ground truth and reward systems that delete disfluencies, ignoring verbatim faithfulness. We
benchmark 11 ASR models from encoder-decoder, CTC and transducer families using both verbatim and intended references on atypical stuttered
speech as a case study. Our quantitative assessment underlines the disparity in model performance and rankings using the two transcript styles. Through this analysis, we highlight the importance of selecting a suitable transcription reference for valid model selection depending on the use-case, particularly for atypical ASR.
Read the full abstract ▾
Computation and Language
When Reranking Hurts: Uncertainty-Based Gating for Few-Shot Reranking
Orian Dabod, Amir DN Cohen and Gabriel Stanovsky
Few-shot selection typically assumes that reranking retrieved examples always improves performance. We challenge this view by identifying that the expensive reranking step can in fact degrade performance. Instead, we propose Training-Free Gated Reranking, which decides whether to rerank the few-shot examples based on the model's uncertainty. Extensive experiments across 8 LLMs, covering 7 NLU
datasets and 18 MT domain-direction combinations, demonstrate that our approach reduces average computational costs by approximately 20% for MT and 54% for NLU at a calibrated operating point, while matching the performance of full reranking. These findings indicate that higher computational cost does not guarantee better performance, and that reranking is most beneficial when targeted at high-uncertainty instances.
Read the full abstract ▾
Computation and Language · Cross-listed from cs.DL
Usage frequency and application variety of research methods in library and information science: Continuous investigation from 1991 to 2021
Chengzhi Zhang, Liang Tian and Heting Chu
The present study analyzed over 26,000 research articles published between 1991 and 2021 in twenty-one major LIS (Library and Information Science) journals, using the machine learning (ML) approach to categorize the research methods used by LIS scholars. The findings of this study are significant. Firstly, there has been a shift in the research strategy from conceptual research (e.g., "Theoretical approach") to empirical research (e.g., "Interview") in LIS investigations over the past 31 years. Secondly, the research topics explored by LIS scholars during this period have moved from system-centered issues (e.g., "Information
retrieval/models and
algorithms") to user-centered topics (e.g., "Information services "). Thirdly, the study revealed dynamic and revealing relationships between the 18 research topics identified in the study and the 16 research methods commonly adopted in the LIS field. These dynamic relationships can be visualized by year and longitudinally via an interactive map created in this study.
Read the full abstract ▾
Computation and Language
Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks
Guangsheng Bao, Lihua Rong, Yanbin Zhao et al. (+3 more)
Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two
benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the
adversarial RAID. This framework marks a pioneering effort in statistical methods to enhance detection reliability against attacks. We release our data and code at https://github.com/baoguangsheng/triospect.
Read the full abstract ▾
All authors Guangsheng Bao, Lihua Rong, Yanbin Zhao, Xiao Yu, Qiji Zhou, Yue Zhang
Computation and Language
Building a Multimodal Dataset of Academic Paper for Keyword Extraction
Jingyu Zhang, Xinyi Yan, Yi Xiang et al. (+2 more)
Up to this point, keyword extraction task typically relies solely on textual data. Neglecting visual details and audio features from image and audio modalities leads to deficiencies in information richness and overlooks potential correlations, thereby constraining the model's ability to learn representations of the data and the accuracy of model predictions. Furthermore, the currently available
multimodal datasets for keyword extraction task are particularly scarce, further hindering the progress of research on
multimodal keyword extraction task. Therefore, this study constructs a
multimodal dataset of academic paper consisting of 1000 samples, with each sample containing paper text, images, audios and keywords. Based on unsupervised and supervised methods of keyword extraction, experiments are conducted using textual data from papers, as well as text extracted from images and audio. The aim is to investigate the differences in performance in keyword extraction task with respect to different modal information and the fusion of
multimodal information. The experimental results indicate that text from different modalities exhibits distinct characteristics in the model. The concatenation of paper text, image text and audio text can effectively enhance the keyword extraction performance of academic papers.
Read the full abstract ▾
All authors Jingyu Zhang, Xinyi Yan, Yi Xiang, Yingyi Zhang, Chengzhi Zhang
Computation and Language
Exploring the relationship between team institutional composition and novelty in academic papers based on fine-grained knowledge entities
Ziling Chen, Chengzhi Zhang, Heng Zhang et al. (+3 more)
The composition of author teams is an important factor influencing the novelty of academic papers. However, existing studies have paid limited
attention to the role of institutional composition, and most novelty measures remain at a general level, making it difficult to explain the specific sources and types of novelty in papers. Taking the field of natural
language processing as an example, this study investigates the relationship between team institutional composition and the fine-grained novelty of academic papers. Author teams are classified into three types: academic institutions, industrial institutions, and mixed academic and industrial institutions. Four types of fine-grained knowledge entities are extracted from full-text papers, including methods,
datasets, tools, and metrics. The novelty of papers is then measured based on entity combinations, and pairwise combinations of different entity types are further analyzed to examine their contributions to novel papers. The results show that, in the field of natural
language processing, collaboration between industrial and academic institutions is more likely to produce novel papers than purely industrial collaboration. From the perspective of fine-grained knowledge entities, mixed academic and industrial teams pay more
attention to the novelty of method-metric combinations, whereas industrial teams pay more
attention to the novelty of method-tool combinations. This study reveals the relationship between institutional team composition and paper novelty through fine-grained novelty measurement, providing useful evidence for improving paper quality and promoting industry-academia-research collaboration.
Read the full abstract ▾
All authors Ziling Chen, Chengzhi Zhang, Heng Zhang, Yi Zhao, Chen Yang, Yang Yang
Computation and Language
Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems
Ashish Hallur, Thomas Thebaud, Georgi Tinchev et al. (+2 more)
Speech-to-
speech (S2S) AI
agents are advancing rapidly, yet evaluation lacks interpretable
speech-native measures for conversational prosody and rhythm. Because $F_0$, speaking rate, articulation rate, and pausing shift with model-predicted speaker traits and interaction state, pooled human statistics can be poorly calibrated for evaluating a particular output. Using 4000+ hours of dyadic English conversation from the Seamless Interaction
dataset, we construct matched reference regimes for $F_0$ mean, $F_0$ expressivity,
speech rate, articulation rate, pause ratio, and mean pause duration. We then define a percentile-based evaluation protocol: extract the same metrics from an S2S output waveform, compare them to the closest matched human reference stratum, and report percentile deviations or 5th-95th percentile out-of-regime flags. On held-out human rows, pooled references over-flag state-conditioned $F_0$ expressivity and rhythm, while matched references return flag rates closer to the nominal 10% and make deviation direction interpretable. These outputs serve as behavioral plausibility checks that complement, rather than replace, perceptual and user-centered evaluation.
Read the full abstract ▾
All authors Ashish Hallur, Thomas Thebaud, Georgi Tinchev, Venkatesh Ravichandran, Laureano Moro-Velazquez
Computation and Language · Cross-listed from cs.CV
ADAPT: Attention Dynamics Alignment with Preference Tuning for Faithful MLLMs
Zhiyuan Yao, Zheren Fu, Zhixiao Zheng et al. (+3 more)
Multimodal Large
Language Models (MLLMs) are critically hampered by
hallucination, generating content inconsistent with the provided image. In this paper, we identify an internal signature of
hallucination: progressive degradation of text-to-image cross-
attention during generation, leading to specific failure patterns like unfocused or biased
attention. Existing mitigation strategies are largely outcome-driven and do not explicitly target this failure mode. To address this problem, we propose ADAPT (
Attention Dynamics
Alignment with Preference Tuning), an
attention-based framework that intervenes directly on text-to-image cross-
attention dynamics. We propose ADAPT with three key contributions: a cross-
attention visual anchor refined from early decoding to provide stable spatial grounding, an
attention-supervised inference mechanism that detects and corrects
attention drift online, and a Visual
Attention Guidance DPO that aligns preferences toward visually grounded responses. Experiments show that each component of ADAPT contributes to
hallucination reduction, and the full framework achieves new best results across multiple
hallucination benchmarks, reducing
hallucination rates by 40%-60% across mainstream backbones while preserving general
multimodal capabilities. Our work provides an
attention-based perspective on mitigating
hallucinations by exploring the model's internal text-to-image cross-
attention behaviors. Code is available at https://github.com/yao-ustc/ADAPT
Read the full abstract ▾
All authors Zhiyuan Yao, Zheren Fu, Zhixiao Zheng, Jiajun Li, Yi Tu, Zhendong Mao