Machine Learning
Fairness-informed Pareto Optimization : An Efficient Bilevel Framework
Sofiane Tanji, Samuel Vaiter and Yassine Laguel
Despite their promise, fair machine learning methods often yield Pareto-inefficient models, in which the performance of certain groups can be improved without degrading that of others. This issue arises frequently in traditional in-processing approaches such as
fairness-through-regularization. In contrast, existing Pareto-efficient approaches are biased towards a certain perspective on
fairness and fail to adapt to the broad range of
fairness metrics studied in the literature. In this paper, we present BADR, a simple framework to recover the optimal Pareto-efficient model for any
fairness metric. Our framework recovers its models through a Bilevel Adaptive Rescalarisation procedure. The lower level is a weighted empirical risk minimization task where the weights are a convex combination of the groups, while the upper level optimizes the chosen
fairness objective. We equip our framework with two novel large-scale, single-loop
algorithms, BADR-GD and BADR-SGD, and establish their convergence guarantees. We release badr, an open-source Python toolbox implementing our framework for a variety of learning tasks and
fairness metrics. Finally, we conduct extensive numerical experiments demonstrating the advantages of BADR over existing Pareto-efficient approaches to
fairness.
Read the full abstract ▾
Machine Learning
BladeSDF : Unconditional and Conditional Generative Modeling of Representative Blade Geometries Using Signed Distance Functions
Ashish S. Nair, Sandipp Krishnan Ravi, Itzel Salgado et al. (+3 more)
Generative AI has emerged as a transformative paradigm in engineering design, enabling automated synthesis and reconstruction of complex 3D geometries while preserving feasibility and performance relevance. This paper introduces a domain-specific implicit generative framework for turbine blade geometry using DeepSDF, addressing critical gaps in performance-aware modeling and manufacturable design generation. The proposed method leverages a continuous signed distance function (SDF) representation to reconstruct and generate smooth, watertight geometries with quantified accuracy. It establishes an interpretable, near-Gaussian latent space that aligns with blade-relevant parameters, such as taper and chord ratios, enabling controlled exploration and unconditional synthesis through interpolation and Gaussian sampling. In addition, a compact neural network maps engineering descriptors, such as maximum directional strains, to latent codes, facilitating the generation of performance-informed geometry. The framework achieves high reconstruction fidelity, with surface distance errors concentrated within $1\%$ of the maximum blade dimension, and demonstrates robust generalization to unseen designs. By integrating constraints, objectives, and performance metrics, this approach advances beyond traditional 2D-guided or unconstrained 3D pipelines, offering a practical and interpretable solution for data-driven turbine blade modeling and concept generation.
Read the full abstract ▾
All authors Ashish S. Nair, Sandipp Krishnan Ravi, Itzel Salgado, Changjie Sun, Sayan Ghosh, Liping Wang
Machine Learning · Cross-listed from cs.CL
MOSLD-Bench: Multilingual Open-Set Learning and Discovery Benchmark for Text Categorization
Adriana-Valentina Costache, Daria-Nicoleta Dragomir, Silviu-Florin Gheorghe et al. (+3 more)
Open-set learning and discovery (OSLD) is a challenging machine learning task in which samples from new (unknown) classes can appear at test time. It can be seen as a generalization of zero-shot learning, where the new classes are not known a priori, hence involving the active discovery of new classes. While zero-shot learning has been extensively studied in text classification, especially with the emergence of pre-trained
language models, open-set learning and discovery is a comparatively new setup for the text domain. To this end, we introduce the first
multilingual open-set learning and discovery (MOSLD)
benchmark for text categorization by topic, comprising 960K data samples across 12
languages. To construct the
benchmark, we (i) rearrange existing
datasets and (ii) collect new data samples from the news domain. Moreover, we propose a novel framework for the OSLD task, which integrates multiple stages to continuously discover and learn new classes. We evaluate several
language models, including our own, to obtain results that can be used as reference for future work. We release our
benchmark at https://github.com/Adriana19Valentina/MOSLD-Bench.
Read the full abstract ▾
All authors Adriana-Valentina Costache, Daria-Nicoleta Dragomir, Silviu-Florin Gheorghe, Eduard Poesina, Paul Irofti, Radu Tudor Ionescu
Machine Learning · Cross-listed from stat.ML
Distribution-Free Confidence Ellipsoids for Ridge Regression with PAC Bounds
Szabolcs Szentpéteri and Balázs Csanád Csáji
Linearly parametrized models are widely used in control and signal processing, with the least-squares (LS) estimate being the archetypical solution. When the input is insufficiently exciting, the LS problem may be unsolvable or numerically unstable. This issue can be resolved through regularization, typically with ridge regression. Although regularized
estimators reduce the variance error, it remains important to quantify their estimation uncertainty. A possible approach for linear regression is to construct confidence ellipsoids with the Sign-Perturbed Sums (SPS) ellipsoidal outer approximation (EOA)
algorithm. The SPS EOA builds non-asymptotic confidence ellipsoids under the assumption that the noises are independent and symmetric about zero. This paper introduces an extension of the SPS EOA
algorithm to ridge regression, and derives probably approximately correct (PAC) upper bounds for the resulting region sizes. Compared with previous analyses, our result explicitly show how the regularization parameter affects the region sizes, and provide tighter bounds under weaker excitation assumptions. Finally, the practical effect of regularization is also demonstrated via simulation experiments.
Read the full abstract ▾
Machine Learning
A Learnable Wavelet Transformer for Long-Short Equity Trading and Risk-Adjusted Return Optimization
Shuozhe Li, Du Cheng and Leqi Liu
Learning profitable intraday trading policies from financial time series is challenging due to heavy noise, non-stationarity, and strong cross-sectional dependence among related assets. We propose WaveLSFormer, a learnable wavelet-based long-short
Transformer that jointly performs multi-scale decomposition and return-oriented decision learning. Unlike standard time-series
forecasting that optimizes prediction error and typically requires a separate position-sizing or portfolio-construction step, our model directly outputs a
market-neutral long/short portfolio and is trained end-to-end on a trading objective with risk-aware regularization. Specifically, a learnable wavelet front-end generates low-/high-frequency components via an end-to-end trained filter bank, guided by spectral regularizers that encourage stable and well-separated frequency bands. To fuse multi-scale information, we introduce a low-guided high-frequency injection (LGHI) module that refines low-frequency representations with high-frequency cues while controlling training stability. The model outputs a portfolio of long/short positions that is rescaled to satisfy a fixed risk budget and is optimized directly with a trading objective and risk-aware regularization. Extensive experiments on five years of hourly data across six industry groups, evaluated over ten random seeds, demonstrate that WaveLSFormer consistently outperforms MLP, LSTM and
Transformer backbones, with and without fixed discrete wavelet front-ends. On average in all industries, WaveLSFormer achieves a cumulative overall strategy return of $0.607 \pm 0.045$ and a Sharpe ratio of $2.157 \pm 0.166$, substantially improving both profitability and risk-adjusted returns over the strongest baselines.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Who Endorsed It? Measuring Authority Bias Across Expertise Levels in Language Models
Priyanka Mary Mammen, Emil Joswin and Shankar Venkitachalam
Prior research demonstrates that performance of
language models on
reasoning tasks can be influenced by suggestions, hints and endorsements. However, the influence of endorsement source credibility remains underexplored. We investigate whether
language models exhibit systematic bias based on the perceived expertise of the provider of the endorsement. Across 4
datasets spanning mathematical, legal, and medical
reasoning, we evaluate 11 models using personas representing four expertise levels per domain. Our results reveal that models are increasingly susceptible to incorrect/misleading endorsements as source expertise increases, with higher-authority sources inducing not only accuracy degradation but also increased confidence in wrong answers. We also show that this authority bias is mechanistically encoded within the model and a model can be steered away from the bias, thereby improving its performance even when an expert gives a misleading endorsement.
Read the full abstract ▾
Machine Learning
TrustEnergy: A Unified Framework for Accurate and Reliable User-level Energy Usage Prediction
Dahai Yu, Rongchao Xu, Dingyi Zhuang et al. (+3 more)
Energy usage prediction is important for various real-world applications, including grid management, infrastructure planning, and disaster response. Although a plethora of deep learning approaches have been proposed to perform this task, most of them either overlook the essential spatial correlations across households or fail to scale to individualized prediction, making them less effective for accurate fine-grained user-level prediction. In addition, due to the dynamic and uncertain nature of energy usage caused by various factors such as extreme weather events, quantifying uncertainty for reliable prediction is also significant, but it has not been fully explored in existing work. In this paper, we propose a unified framework called TrustEnergy for accurate and reliable user-level energy usage prediction. There are two key technical components in TrustEnergy, (i) a Hierarchical Spatiotemporal Representation module to efficiently capture both macro and micro energy usage patterns with a novel
memory-augmented spatiotemporal graph neural network, and (ii) an innovative Sequential Conformalized
Quantile Regression module to dynamically adjust uncertainty bounds to ensure valid prediction intervals over time, without making strong assumptions about the underlying data distribution. We implement and evaluate our TrustEnergy framework by working with an electricity provider in Florida, and the results show our TrustEnergy can achieve a 5.4% increase in prediction accuracy and 5.7% improvement in uncertainty quantification compared to state-of-the-art baselines.
Read the full abstract ▾
All authors Dahai Yu, Rongchao Xu, Dingyi Zhuang, Yuheng Bu, Shenhao Wang, Guang Wang
Machine Learning · Cross-listed from cs.CG
Classifiers in High Dimensional Hilbert Metrics
Aditya Acharya, Auguste H. Gezalyan and David M. Mount
Classifying points in high dimensional spaces is a fundamental
geometric problem in machine learning. In this paper, we address classifying points in the $d$-dimensional
Hilbert polygonal metric. The
Hilbert metric is a generalization of the Cayley-Klein
hyperbolic distance to arbitrary convex bodies and has a diverse range of applications in machine learning and convex geometry. We first present an efficient LP-based
algorithm in the metric for the large-margin SVM problem. Our
algorithm runs in time
polynomial to the number of points, bounding facets, and dimension. This is a significant improvement on previous works, which either provide no theoretical guarantees on running time, or suffer from exponential runtime. We also consider the closely related Funk metric. We also present efficient
algorithms for the soft-margin SVM problem and for nearest neighbor-based classification in the
Hilbert metric.
Read the full abstract ▾
Machine Learning
Can LLMs Compress (and Decompress)? Evaluating Code Understanding and Execution via Invertibility
Nickil Maveli, Antonio Vergari and Shay B. Cohen
LLMs demonstrate strong performance on code
benchmarks, yet consistent
reasoning across forward and backward execution remains elusive. We present RoundTripCodeEval (RTCE), a
benchmark of four code execution
reasoning tasks that evaluates round-trip consistency through execution-free, exact-match assessment of bijection fidelity across four lossless compression
algorithms. We evaluate state-of-the-art Code-LLMs under zero-shot prompting, supervised fine-tuning on execution traces, and iterative self-reflection. All approaches yield only modest improvements and none closes the gap, revealing that current LLMs lack the internal coherence required for reliable bidirectional code
reasoning. RTCE surfaces findings invisible to existing
benchmarks: models frequently pass individual forward and backward tasks yet fail the combined round-trip, exposing mutually inconsistent internal representations; SFT and self-reflection saturate after one revision round, indicating they cannot repair fundamental algorithmic misunderstandings; and failures persist even on simple bijections such as RLE, suggesting that algorithmic complexity is not the sole root cause.\footnote{Code and
dataset are available at https://github.com/Nickil21/round-trip-code-compression.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Confidence over Time: Confidence Calibration with Temporal Logic for Large Language Model Reasoning
Zhenjiang Mao, Anirudhh Venkat, Artem Bisliouk et al. (+4 more)
Large
Language Models (LLMs) increasingly rely on long-form, multi-step
reasoning to solve complex tasks such as mathematical problem solving and scientific question answering. Despite strong performance, existing confidence estimation methods typically reduce an entire
reasoning process to a single scalar score, ignoring how confidence evolves throughout the generation. As a result, these methods are often sensitive to superficial factors such as response length or verbosity, and struggle to distinguish correct
reasoning from confidently stated errors. We propose to characterize the stepwise confidence signal using Signal Temporal Logic (STL). Using a discriminative STL mining procedure, we discover temporal formulas that distinguish confidence signals of correct and incorrect responses. Our analysis found that the STL patterns generalize across tasks, and numeric parameters exhibit sensitivity to individual questions. Based on these insights, we develop a confidence estimation approach that informs STL blocks with parameter hypernetworks. Experiments on multiple
reasoning tasks show our confidence scores are more calibrated than the baselines.
Read the full abstract ▾
All authors Zhenjiang Mao, Anirudhh Venkat, Artem Bisliouk, Akshat Kothiyal, Sindhura Kumbakonam Subramanian, Saithej Singhu, Ivan Ruchkin
Machine Learning · Cross-listed from cs.CL
Recurrent Confidence Chain: Temporal-Aware Uncertainty Quantification in Large Language Models
Zhenjiang Mao and Anirudhh Venkat
As
reasoning modules, such as the chain-of-thought mechanism, are applied to large
language models, they achieve strong performance on various tasks such as answering common-sense questions and solving math problems. The main challenge now is to assess the uncertainty of answers, which can help prevent misleading or serious
hallucinations for users. Although current methods analyze long
reasoning sequences by filtering unrelated
tokens and examining potential connections between nearby
tokens or sentences, the temporal spread of confidence is often overlooked. This oversight can lead to inflated overall confidence, even when earlier steps exhibit very low confidence. To address this issue, we propose a novel method that incorporates inter-step
attention to analyze semantic correlations across steps. For handling long-horizon responses, we introduce a hidden confidence mechanism to retain historical confidence information, which is then combined with stepwise confidence to produce a more accurate overall estimate. We evaluate our method on the GAOKAO math
benchmark and the CLadder causal
reasoning dataset using mainstream open-source large
language models. Our approach is shown to outperform state-of-the-art methods by achieving a superior balance between predictive quality and calibration, demonstrated by strong performance on both Negative Log-Likelihood and Expected Calibration Error.
Read the full abstract ▾
Machine Learning
CausationEntropy: Pythonic Optimal Causation Entropy
Kevin Slote, Jeremie Fish and Erik Bollt
Optimal Causation
Entropy (oCSE) is a robust causal network modeling technique that reveals causal networks from dynamical systems and coupled oscillators, distinguishing direct from indirect paths. CausationEntropy is a Python package that implements oCSE and several of its significant optimizations and methodological extensions. In this paper, we introduce the version 1.1 release of CausationEntropy, which includes new synthetic data generators, plotting tools, and several advanced information-theoretical causal network discovery
algorithms with criteria for estimating Gaussian, k-nearest neighbors (kNN),
geometric k-nearest neighbors (
geometric-kNN), kernel density (KDE) and Poisson entropic
estimators. The package is easy to install from the PyPi software repository, is thoroughly documented, supplemented with extensive code examples, and is modularly structured to support future additions. The entire codebase is released under the MIT license and is available on GitHub and through PyPi Repository. We expect this package to serve as a
benchmark tool for causal discovery in complex dynamical systems.
Read the full abstract ▾
Machine Learning · Cross-listed from stat.AP
Improving Geopolitical Forecasts with Bayesian Networks
Matthew Martin
This study explores how
Bayesian networks (BNs) can improve forecast accuracy compared to logistic regression and recalibration and aggregation methods, using data from the Good Judgment Project. Regularized logistic regression models and a baseline recalibrated aggregate were compared to two types of BNs: structure-learned BNs with arcs between predictors, and naive BNs. Four predictor variables were examined: absolute difference from the aggregate, forecast value, days prior to question close, and mean standardized Brier score. Results indicated the recalibrated aggregate achieved the highest accuracy (AUC = 0.985), followed by both types of BNs, then the logistic regression models. Performance of the BNs was likely harmed by reduced information from the discretization process and violation of the assumption of linearity likely harmed the logistic regression models. Future research should explore hybrid approaches combining BNs with logistic regression, examine additional predictor variables, and account for hierarchical data dependencies.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization
Asen Dotsinski and Panagiotis Eustratiadis
Prefill attacks are an effective and low-cost jailbreaking method, as they directly insert an acceptance sequence (e.g., "Sure, here is...") at the start of an LLM's output and lead the model to continue the response. We make two contributions to this prior work. First, we show that an unsophisticated adversary can improve the well-known prefill attacks by ensembling a small number of prefill variants. Running three easy-to-generate prefills yields a combined attack success rate (ASR) of 22%, 90%, and 99% on Gemma-7B, Llama-3.1-8B, and Qwen3-8B respectively, an up to 38 percentage point improvement over the standard "Sure, here's..." prefill and up to 82 percentage points over our reproduction of GCG (Zou et al., 2023). Second, we introduce "sockpuppetting", a hybrid attack that optimizes an
adversarial suffix placed inside the "assistant" message block of the chat template, rather than within the user
prompt. The rolling variant of this attack, RollingSockpuppetGCG, increases
prompt-agnostic ASR by up to 64 percentage points over our universal GCG baseline on Llama-3.1-8B. An ablation indicates that part of this gain stems from the choice of acceptance sequence rather than suffix placement alone (Appendix F). Both findings highlight the need for defences against output-prefix injection in open-weight models. Code: https://gitlab.com/asendotsinski/sockpuppetting
Read the full abstract ▾
Machine Learning · Cross-listed from cs.AI
The Geometry of Thought: How Scale Restructures Reasoning In Large Language Models
Samuel Cyrenius Anderson
Scale does not uniformly improve
reasoning - it restructures it. Analyzing 25,000+ chain-of-thought trajectories across four domains (Law, Science, Code, Math) and two scales (8B, 70B parameters), we discover that neural scaling laws trigger domain-specific phase transitions rather than uniform capability gains. Legal
reasoning undergoes Crystallization: 45% collapse in representational dimensionality (d95: 501 -> 274), 31% increase in trajectory
alignment, and 10x
manifold untangling. Scientific and mathematical
reasoning remain
Liquid - geometrically invariant despite 9x parameter increase. Code
reasoning forms a discrete
Lattice of strategic modes (silhouette: 0.13 -> 0.42). This geometry predicts learnability. We introduce Neural
Reasoning Operators - learned mappings from initial to terminal hidden states. In crystalline legal
reasoning, our operator achieves 63.6% accuracy on held-out tasks via probe decoding, predicting
reasoning endpoints without traversing intermediate states. We further identify a universal oscillatory signature (coherence ~ -0.4) invariant across domains and scales, suggesting
attention and feedforward layers drive
reasoning through opposing dynamics. These findings establish that the cost of thought is determined not by task difficulty but by
manifold geometry - offering a blueprint for inference acceleration where
topology permits.
Read the full abstract ▾
Machine Learning
On the Relation of State Space Models and Hidden Markov Models
Aydin Ghojogh, M.Hadi Sepanj and Benyamin Ghojogh
State Space Models (SSMs) and Hidden Markov Models (HMMs) are foundational frameworks for modeling sequential data with latent variables and are widely used in signal processing, control theory, and machine learning. Despite their shared temporal structure, they differ fundamentally in the nature of their latent states, probabilistic assumptions, inference procedures, and training paradigms. Recently, deterministic state space models have re-emerged in natural
language processing through architectures such as S4 and Mamba, raising new questions about the relationship between classical probabilistic SSMs, HMMs, and modern neural sequence models. In this paper, we present a unified and systematic comparison of HMMs, linear Gaussian state space models, Kalman filtering, and contemporary NLP state space models. We analyze their formulations through the lens of probabilistic graphical models, examine their inference
algorithms – including forward-backward inference and Kalman filtering – and contrast their learning procedures via Expectation-Maximization and gradient-based optimization. By highlighting both structural similarities and semantic differences, we clarify when these models are equivalent, when they fundamentally diverge, and how modern NLP SSMs relate to classical probabilistic models. Our analysis bridges perspectives from control theory, probabilistic modeling, and modern deep learning.
Read the full abstract ▾
Machine Learning
Beyond Mapping : Domain-Invariant Representations via Spectral Embedding of Optimal Transport Plans
Abdel Djalil Sad Saoud, Fred Maurice Ngolè Mboula and Hanane Slimani
Distributional shifts between training and inference time data remain a central challenge in machine learning, often leading to poor performance. It motivated the study of principled approaches for domain
alignment, such as optimal transport based unsupervised domain adaptation, that relies on approximating Monge map using transport plans, which is sensitive to the transport problem regularization strategy and hyperparameters, and might yield biased domains
alignment. In this work, we propose to interpret smoothed transport plans as adjacency
matrices of bipartite graphs connecting source to target domain and derive domain-invariant samples' representations through spectral
embedding. We evaluate our approach on acoustic adaptation
benchmarks for music genre recognition, music-
speech discrimination, as well as electrical cable defect detection and classification tasks using time domain reflection in different diagnosis settings, achieving overall strong performances.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CV
MultiST: A Cross-Attention-Based Multimodal Model for Spatial Transcriptomic
Wei Wang, Quoc-Toan Ly, Chong Yu et al. (+1 more)
Spatial transcriptomics (ST) enables transcriptome-wide profiling while preserving the spatial context of tissues, offering unprecedented opportunities to study tissue organization and
cell-
cell interactions in situ. Despite recent advances, existing methods often lack effective integration of histological morphology with molecular profiles, relying on shallow fusion strategies or omitting tissue images altogether, which limits their ability to resolve ambiguous spatial domain boundaries. To address this challenge, we propose MultiST, a unified
multimodal framework that jointly models spatial
topology, gene expression, and tissue morphology through cross-
attention-based fusion. MultiST employs graph-based gene encoders with
adversarial alignment to learn robust spatial representations, while integrating color-normalized histological features to capture molecular-morphological dependencies and refine domain boundaries. We evaluated the proposed method on 13 diverse ST
datasets spanning two organs, including human
brain cortex and breast cancer tissue. MultiST yields spatial domains with clearer and more coherent boundaries than existing methods, leading to more stable pseudotime trajectories and more biologically interpretable
cell-
cell interaction patterns. The MultiST framework and source code are available at https://github.com/LabJunBMI/MultiST.git.
Read the full abstract ▾
All authors Wei Wang, Quoc-Toan Ly, Chong Yu, Jun Bai
Machine Learning · Cross-listed from cs.CL
Paid Voices vs. Public Feeds: Interpretable Cross-Platform Theme-Based Analysis of Climate Discourse
Samantha Sudhoff, Pranav Perumal, Zhaoqing Wu et al. (+1 more)
Climate discourse online shapes public understanding of
climate change and informs political and policy debate, yet it unfolds across structurally different environments: paid advertising platforms host targeted, institutionally produced messaging, while public social media reflects largely organic, user-driven discussion. We present a comparative analysis of
climate discourse across paid advertisements on Meta (previously Facebook) and public posts on Bluesky from July 2024 to September 2025. To support it, we develop an interpretable thematic discovery pipeline that clusters texts by semantic similarity and uses large
language models (LLMs) to label clusters with concise, human-interpretable themes, requiring no predefined topic inventory or seed set. Using these themes, we find the two environments diverge systematically: paid advertising centers on strategic promotion of specific solutions in a formal, forward-looking register, whereas organic discourse centers on systemic critique in a crisis-oriented, scientifically grounded one. We also evaluate the utility of the discovered themes through downstream stance prediction and theme-guided
retrieval tasks. While our analysis focuses on
climate communication, the framework generalizes to comparative thematic analysis across heterogeneous communication environments.
Read the full abstract ▾
All authors Samantha Sudhoff, Pranav Perumal, Zhaoqing Wu, Tunazzina Islam
Machine Learning · Cross-listed from hep-ph
Scaling laws for amplitude surrogates
Henning Bahl, Victor Bresó-Pla, Anja Butter et al. (+1 more)
Scaling laws describing the dependence of neural network performance on the amount of training data, the spent compute, and the network size have emerged across a huge variety of machine learning task and
datasets. In this work, we systematically investigate these scaling laws in the context of amplitude surrogates for particle physics. We show that the scaling coefficients are connected to the number of external particles of the process. Our results demonstrate that scaling laws are a useful tool to achieve desired precision targets.
Read the full abstract ▾
All authors Henning Bahl, Victor Bresó-Pla, Anja Butter, Joaquín Iturriza Ramirez
Machine Learning
On the Extreme Variance of Certified Local Robustness Across Model Seeds
Minh Le and Phuong Cao
Robustness verification of neural networks, referring to formally proving that neural networks satisfy robustness properties, is of crucial importance in safety-critical applications, where model failures can result in loss of human life or million-dollar damages. However, the dependability of verification results may be questioned due to sources of randomness in machine learning, and although this has been widely investigated for accuracy, its impact on robustness verification remains unknown. In this paper, we demonstrate a concerning result: Models that differ only in random seeds during training exhibit extreme variance in their certified robustness, with a standard deviation that is statistically larger than the marginal robustness improvements reported in recent machine learning papers. In addition, we also show that certified robustness generalization to unseen data varies significantly across
datasets, falling short of the dependability expectations for safety-critical tasks. Our findings are major concerns because: (i) machine learning results in certified robustness are likely unconvincing due to extreme variance in certified robustness, and (ii) a “lucky” model seed in a test set cannot be guaranteed to maintain its higher certified robustness under a different test set. In light of these results, we urge researchers to increase the reporting of confidence intervals for certified robustness, and we urge those verifying neural networks to be more comprehensive in verification by using large-scale, diverse, and unseen data.
Read the full abstract ▾
Machine Learning
CooperBench: Why Coding Agents Cannot be Your Teammates Yet
Arpandeep Khatua, Hao Zhu, Peter Tran et al. (+8 more)
Resolving team conflicts requires not only task-specific competence, but also social intelligence to find common ground and build consensus. As AI
agents increasingly collaborate on complex work, they must develop coordination capabilities to function as effective teammates. Yet we hypothesize that current
agents lack these capabilities. To test this, we introduce CooperBench, a
benchmark of over 600 collaborative coding tasks across 12 libraries in 4 programming
languages. Each task assigns two
agents different features that can be implemented independently but may conflict without proper coordination. Tasks are grounded in real open-source repositories with expert-written tests. Evaluating state-of-the-art coding
agents, we observe the curse of coordination:
agents achieve on average 30% lower success rates when working together compared to performing both tasks individually. This contrasts sharply with human teams, where adding teammates typically improves productivity. Our analysis reveals three key issues: (1) communication channels become jammed with vague, ill-timed, and inaccurate messages; (2) even with effective communication,
agents deviate from their commitments; and (3)
agents often hold incorrect expectations about others' plans and communication. Through large-scale simulation, we also observe rare but interesting emergent coordination behavior including role division, resource division, and negotiation. Our research presents a novel
benchmark for collaborative coding and calls for a shift from pursuing individual
agent capability to developing social intelligence.
Read the full abstract ▾
All authors Arpandeep Khatua, Hao Zhu, Peter Tran, Arya Prabhudesai, Frederic Sadrieh, Johann K. Lieberwirth, Xinkai Yu, Yicheng Fu, Michael J. Ryan, Jiaxin Pei, Diyi Yang
Machine Learning · Cross-listed from cs.SI
The Tag is the Signal: URL-Agnostic Credibility Scoring for Messages on Telegram
Yipeng Wang, Huy Gia Han Vu and Mohit Singhal
Telegram has become one of the leading platforms for disseminating misinformational messages. However, many existing pipelines still classify each message's credibility based on the reputation of its associated domain names or its lexical features. Such methods work well on traditional long-form news articles published by well-known sources, but high-risk posts on Telegram are short and URL-sparse, leading to failures for link-based and standard TF-IDF models. To this end, we propose the TAG2CRED pipeline, a method designed for such short, convoluted messages. Our model will directly score each post based on the tags assigned to the text. We designed a concise label system that covers the dimensions of theme, claim type, call to action, and evidence. The fine-tuned large
language model (LLM) assigns tags to messages and then maps these tags to calibrated risk scores in the [0,1] interval through L2-regularized logistic regression. We evaluated 87,936 Telegram messages associated with Media Bias/Fact Check (MBFC), using URL masking and domain disjoint splits. The results showed that the ROC-AUC of the TAG2CRED model reached 0.871, the macro-F1 value was 0.787, and the Brier score was 0.167, outperforming the baseline TF-IDF (macro-F1 value 0.737, Brier score 0.248); at the same time, the number of features used in this model is much smaller, and the generalization ability on infrequent domains is stronger. The performance of the stacked ensemble model (TF-IDF + TAG2CRED + SBERT) was further improved over the baseline SBERT. ROC-AUC reached 0.901, and the macro-F1 value was 0.813 (Brier score 0.114). This indicates that style labels and lexical features may capture different but complementary dimensions of information risk.
Read the full abstract ▾
Machine Learning
Balancing Classification and Calibration Performance in Decision-Making LLMs via Calibration Aware Reinforcement Learning
Duygu Nur Yaldiz, Evangelia Spiliopoulou, Zheng Qi et al. (+3 more)
Large
language models (LLMs) are increasingly deployed in decision-making tasks, where not only accuracy but also reliable confidence estimates are essential. Well-calibrated confidence enables downstream systems to decide when to trust a model and when to defer to fallback mechanisms. In this work, we conduct a systematic study of calibration in two widely used fine-tuning paradigms: supervised fine-tuning (SFT) and reinforcement learning with verifiable rewards (RLVR). We show that while RLVR improves task performance, it produces extremely overconfident models, whereas SFT yields substantially better calibration, even under distribution shift, though with smaller performance gains. Through targeted experiments, we diagnose RLVR's failure, showing that decision
tokens act as extraction steps of the decision in
reasoning traces and do not carry confidence information, which prevents reinforcement learning from surfacing calibrated alternatives. Based on this insight, we propose a calibration-aware reinforcement learning formulation that directly adjusts decision-
token probabilities. Our method preserves RLVR's accuracy level while mitigating overconfidence, reducing ECE scores up to 9 points.
Read the full abstract ▾
All authors Duygu Nur Yaldiz, Evangelia Spiliopoulou, Zheng Qi, Siddharth Varia, Srikanth Doss, Nikolaos Pappas
Machine Learning
Multi-level Monte Carlo Dropout for Efficient Uncertainty Quantification
Aaron Pim and Tristan Pryer
We develop a multilevel Monte Carlo (MLMC) framework for uncertainty quantification with Monte Carlo dropout. Treating dropout masks as a source of epistemic randomness, we define a fidelity hierarchy by the number of
stochastic forward passes used to estimate predictive moments. We construct coupled coarse–fine
estimators by reusing dropout masks across fidelities, yielding telescoping MLMC
estimators for both predictive means and predictive variances that remain unbiased for the corresponding dropout-induced quantities while reducing sampling variance at fixed evaluation budget. We derive explicit bias, variance and effective cost expressions, together with sample-allocation rules across levels. Numerical experiments on forward and inverse PINNs–Uzawa
benchmarks confirm the predicted variance rates and demonstrate efficiency gains over single-level MC-dropout at matched cost.
Read the full abstract ▾
Machine Learning · Cross-listed from cs.CL
Stop Taking Tokenizers for Granted: They Are Core Design Decisions in Large Language Models
Sawsan Alqahtani, Mir Tafseer Nayeem, Md Tahmid Rahman Laskar et al. (+2 more)
Tokenization underlies every large
language model, yet it remains an under-theorized and inconsistently designed component. Common subword approaches such as Byte Pair Encoding (BPE) offer scalability but often misalign with linguistic structure, amplify bias, and waste capacity across
languages and domains. This paper reframes tokenization as a core modeling decision rather than a preprocessing step. We argue for a context-aware framework that integrates tokenizer and model co-design, guided by linguistic, domain, and deployment considerations. Standardized evaluation and transparent reporting are essential to make tokenization choices accountable and comparable. Treating tokenization as a core design problem, not a technical afterthought, can yield
language technologies that are fairer, more efficient, and more adaptable.
Read the full abstract ▾
All authors Sawsan Alqahtani, Mir Tafseer Nayeem, Md Tahmid Rahman Laskar, Tasnim Mohiuddin, M Saiful Bari
Machine Learning · Cross-listed from math.NA
Deep Neural networks for solving high-dimensional parabolic partial differential equations
Wenzhong Zhang, Zheyuan Hu, Wei Cai et al. (+1 more)
The numerical solution of high dimensional partial differential equations (PDEs) is severely constrained by the curse of dimensionality (CoD), rendering classical grid–based methods impractical beyond a few dimensions. In recent years, deep neural networks have emerged as a promising mesh free alternative, enabling the approximation of PDE solutions in tens to thousands of dimensions. This review provides a tutorial–oriented introduction to neural–network–based methods for solving high dimensional
parabolic PDEs, emphasizing conceptual clarity and methodological connections. We organize the literature around three unifying paradigms: (i) PDE residual–based approaches, including physicsinformed neural networks and their high dimensional variants; (ii)
stochastic methods derived from Feynman–Kac and backward
stochastic differential equation formulations; and (iii) hybrid derivative–free random difference approaches designed to alleviate the computational cost of derivatives in high dimensions. For each paradigm, we outline the underlying mathematical formulation, algorithmic implementation, and practical strengths and limitations. Representative
benchmark problems–including Hamilton–Jacobi–Bellman and Black–Scholes equations in up to 1000 dimensions –illustrate the scalability, effectiveness, and accuracy of the methods. The paper concludes with a discussion of open challenges and future directions for reliable and scalable solvers of high dimensional PDEs.
Read the full abstract ▾
All authors Wenzhong Zhang, Zheyuan Hu, Wei Cai, George EM Karniadakis
Machine Learning · Cross-listed from cs.CL
A Hybrid Protocol for Large-Scale Semantic Dataset Generation in Low-Resource Languages: The Turkish Semantic Relations Corpus
Ebubekir Tosun, Mehmet Emin Buldur, Özay Ezerceli et al. (+1 more)
We present a hybrid methodology for generating large-scale semantic relationship
datasets in low-resource
languages, demonstrated through a comprehensive Turkish semantic relations corpus. Our approach integrates three phases: (1) FastText
embeddings with Agglomerative Clustering to identify semantic clusters, (2) Gemini 2.5-Flash for automated semantic relationship classification, and (3) integration with curated dictionary sources. The resulting
dataset comprises 843,000 unique Turkish semantic pairs across three relationship types (synonyms, antonyms, co-hyponyms) representing a 10x scale increase over existing resources at minimal cost ($65). We validate the
dataset through two downstream tasks: an
embedding model achieving 90% top-1
retrieval accuracy and a classification model attaining 90% F1-macro. Our scalable protocol addresses critical data scarcity in Turkish NLP and demonstrates applicability to other low-resource
languages. We publicly release the
dataset and models.
Read the full abstract ▾
All authors Ebubekir Tosun, Mehmet Emin Buldur, Özay Ezerceli, Mahmoud ElHussieni
Machine Learning · Cross-listed from cs.CL
Beyond Cosine Similarity: Taming Semantic Drift and Antonym Intrusion in a 15-Million Node Turkish Synonym Graph
Ebubekir Tosun, Mehmet Emin Buldur, Özay Ezerceli et al. (+1 more)
Neural
embeddings have a notorious blind spot: they can't reliably tell synonyms apart from antonyms. Consequently, increasing similarity thresholds often fails to prevent opposites from being grouped together. We've built a large-scale semantic clustering system specifically designed to tackle this problem head on. Our pipeline chews through 15 million lexical items, evaluates a massive 520 million potential relationships, and ultimately generates 2.9 million high-precision semantic clusters. The system makes three primary contributions. First, we introduce a labeled
dataset of 843,000 concept pairs spanning synonymy, antonymy, and co-hyponymy, constructed via Gemini 2.5-Flash LLM augmentation and verified using human-curated dictionary resources. Second, we propose a specialized three-way semantic relation discriminator that achieves 90% macro-F1, enabling robust disambiguation beyond raw
embedding similarity. Third, we introduce a novel soft-to-hard clustering
algorithm that mitigates semantic drift preventing erroneous transitive chains (e.g., hot -> spicy -> pain -> depression) while simultaneously resolving polysemy. Our approach employs a
topology-aware two-stage expansion-
pruning procedure with topological voting, ensuring that each term is assigned to exactly one semantically coherent cluster. The resulting resource enables high-precision semantic search and
retrieval-augmented generation, particularly for morphologically rich and low-resource
languages where existing synonym databases remain sparse.
Read the full abstract ▾
All authors Ebubekir Tosun, Mehmet Emin Buldur, Özay Ezerceli, Mahmoud ElHussieni
Machine Learning · Cross-listed from cs.CL
Aligning Agentic World Models via Knowledgeable Experience Learning
Baochang Ren, Yunzhi Yao, Rui Sun et al. (+3 more)
Current Large
Language Models (LLMs) exhibit a critical modal disconnect: they possess vast semantic knowledge but lack the procedural grounding to respect the immutable laws of the physical world. Consequently, while these
agents implicitly function as world models, their simulations often suffer from physical
hallucinations-generating plans that are logically sound but physically unexecutable. Existing
alignment strategies predominantly rely on resource-intensive training or fine-tuning, which attempt to compress dynamic environmental rules into static model parameters. However, such parametric encapsulation is inherently rigid, struggling to adapt to the open-ended variability of physical dynamics without continuous, costly retraining. To bridge this gap, we introduce WorldMind, a framework that autonomously constructs a symbolic World Knowledge Repository by synthesizing environmental feedback. Specifically, it unifies Process Experience to enforce physical feasibility via prediction errors and Goal Experience to guide task optimality through successful trajectories. Experiments on EB-ALFRED and EB-Habitat demonstrate that WorldMind achieves superior performance compared to baselines with remarkable cross-model and cross-environment transferability.
Read the full abstract ▾
All authors Baochang Ren, Yunzhi Yao, Rui Sun, Shuofei Qiao, Ningyu Zhang, Huajun Chen