Sección

Investigación

Papers y preprints de los feeds de investigación que seguimos.

6415documentos

Published Unlearning Numbers Move Per Checkpoint, and Not Because the Removed Data Survives: An Audit of 263 Released Batch-Normalized Checkpoints

An unlearning audit reads its verdict off numbers that an unlearned model and its retrained reference each publish, and both also ship batch-normalization statistics that no gradient step wrote and no release records. Refitting them on kept data at bit-identical weights moves 47 of 221 released checkpoints past the spread their own release's seeds show, several inside a method whose average does not move: what moves is the checkpoint's property, not its method's. What does the moving is not the removed data surviving in the state: exchanging kept records for removed ones inside a fixed fitting pool moves a published cell by almost nothing, while how far a checkpoint's shipped state has drifted from any refit does track it. The consequence for a published decision is real but narrow: twelve verdicts cross, four clear a measured recalibration budget, two clear it on every replicate, and a population we trained and sited near its own criterion yields none. A release should therefore name the fitting convention beside the number, on the batch-normalized vision models where this channel exists.

arXiv AI Papershace 2 meses

The Convention Gap: Towards Measuring Implicit Communication in Cooperative AI Evaluation

Cooperative AI agents are evaluated against other AIs, yet human cooperation relies on implicit conventions---shared protocols for reading meaning beyond the literal message---which AI-AI benchmarks may not capture. We propose the convention gap, the difference between the failure probability predicted from the literal content of communication and the observed failure rate, as a metric of implicit communication. In the card game Hanabi, the finite deck and deterministic hint constraints make this posterior exactly computable. We replayed about 101,000 play actions from three public datasets of human-human (hanab.live), AI-AI (HOAD), and human-AI (HanabiData) games. The gap was +26.2 percentage points (pp) in human pairs, -0.7~pp in AI pairs, and +16.4~pp in human-AI pairs, and was concentrated on plays of cards that had received no hints (+46~pp in human pairs). Within human-AI play, the literal information available to humans was similar across the three AI partners (mean predicted failure 38--41\%), but human failure rates ranged from 14.4\% to 34.4\% and the gap from +24.1 to +6.2~pp; the partner eliciting the largest gap produced the fewest human failures. Game score carried different information: it depended on each corpus's roster composition, whereas the gap separated human from AI play at the agent level. As a known-answer check, Off-Belief Learning agents, whose convention content is controlled by construction, gave a gap of +1.6~pp at the convention-free level, rising monotonically to +21.7~pp. These results suggest that convention compatibility, rather than AI-AI performance, may predict an AI's effectiveness with human partners.

arXiv AI Papershace 2 meses

ReGround: Grounding Reviewer Comments in Multimodal Evidence

Reviewer comments naturally relate to specific parts of the reviewed paper, yet grounding these comments to the underlying evidence is difficult due to long multimodal documents. Existing benchmarks do not capture this setting and largely focus on explicit, information-seeking queries. We introduce ReGround, a large-scale dataset for reviewer comment grounding that links 10,267 reviewer comments to 16,274 evidence in the original anonymous submission of 3,656 papers. We build on a simple observation: author rebuttals often include explicit references to content of the submission used to address reviewer comments, providing a high-precision annotation source. We cast grounding as a retrieval task and evaluate a wide range of retrieval methods. Results show that retrieval over the entire paper content performs poorly, evidence-type inference is a major bottleneck, and multimodal evidence provides complementary signals that text alone misses. Our dataset exposes grounding reviewer comments as a difficult and practically important problem for scientific document understanding.

arXiv AI Papershace 2 meses

Flexible and Interpretable Accent Distance Measurements

Determining the differences between two speakers' accents is a fundamental task in linguistics and speech technology research. The methodology used to measure these differences depends on the specific research area. A phonetics researcher may demonstrate accent variation by comparing vowel formants in paired recordings of individual words. These results will be interpretable, but the recordings will be time-consuming to collect and may not be representative of connected speech. Accented Text-to-Speech (TTS) research has pushed towards using accent embeddings derived from accent classification tasks. These embeddings can be produced from any speech recording, but are not readily interpretable. In this paper, we demonstrate that articulatory representations created through articulatory inversion can be used as an interpretable basis for accent comparison and that optimal transport provides a framework for accent comparison across arbitrary recording types.

arXiv AI Papershace 2 meses

RouteRepair: Instance-Level Failure Diagnosis and Targeted Repair in LLM-Based Automated Heuristic Design for Routing Optimization

Efficient routing optimization is essential to freight transportation, urban logistics, and shared mobility, where high-quality heuristics are often required under limited computational budgets. Recent large language model (LLM)-based automated heuristic design methods can generate effective routing rules, but aggregate evaluation may mask recurrent failures on particular instance structures. To address this limitation, this study develops RouteRepair, which diagnoses parent-specific weaknesses from instance-level performance and applies targeted modifications to the corresponding heuristic components while protecting behavior that already performs well. Routing evidence, solver behavior, and program context are combined to define bounded repair objectives, and each intervention is validated through matched parent-child evaluation of failure recovery and collateral degradation. Experiments on the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP) span constructive search, guided local search, and ant colony optimization. RouteRepair-GLS reduces the mean TSP optimality gap from 1.7476% to 0.7587%, while the constructive CVRP heuristic lowers average route cost by 1.91% relative to the savings heuristic; the generated ACO priors also outperform matched hand-designed priors. These results show that failure-aware, evidence-constrained refinement can improve routing heuristics on difficult instances while preserving performance on cases they already solve well.

arXiv AI Papershace 2 meses

Cross-Lingual Clinical Annotation Projection as Constrained Text Generation: A Six-Language Study

Background: To determine whether cross-lingual clinical annotation projection can be formulated as a text-preserving, document-level generative task that produces verifiable character-level annotations for multilingual clinical corpus construction, and to characterize its robustness and computational trade-offs relative to candidate-based projection pipelines. Methods: We developed a constrained LLM projection workflow that inserts entity tags directly into immutable target-language text, followed by deterministic validation and character-offset reconstruction. We evaluated it alongside supervised candidate-span projection and hybrid ML-LLM refinement for transferring Spanish Disease, Symptom, and Procedure annotations into six languages. Evaluation used MultiClinAI gold standard with strict span matching and character-overlap F1 Results: Direct LLM projection achieved the strongest and most consistent performance. GLM 5.2 obtained a mean Strict F1 of 0.9201 across 18 language-entity combinations, while locally deployable Gemma4:31B achieved 0.9133. The best LLM configuration improved Strict F1 over the previous state of the art in all 18 settings, by 0.0564-0.1512, yielding 55,416 grounded mentions with reconstructed offsets. Conclusions: Direct LLM-based projection enables high-quality multilingual clinical annotation transfer and provides a practical approach for extending clinical NLP resources to languages with fewer annotated datasets and language-specific tools. Combined with local inference and deterministic validation, it can substantially reduce expert time and cost for multilingual clinical corpus construction.

arXiv AI Papershace 2 meses

Prevalence Determines Precision:Silent Contamination in Detector-Defined Datasets

Many ML datasets are constructed by running a detector, heuristic, or model over candidate pools; accepted items become labels. Dataset precision is then governed by true-positive prevalence in each pool via Bayes, not solely by detector quality. Using one instrument and period, we hold a detector-defined event dataset plus an independent official index labeling every detected item as real or phantom. One detector, three pools yield phantom rates 81.7%, 9.0%, and 0.0%. Transferring precision from the two high-rate pools to the low-rate pool predicts 0.955 versus measured 0.183, a +422% error; the Bayes expression predicts all three within 3.3%. The detected response curve is an exact convex combination of a true-event and a phantom component (residual 1.1e-16), with phantoms outnumbering true events 473 to 308, so contamination is a second signal with detector-inherited shape, not additive noise. Contamination direction depends on the estimator: on identical windows one statistic is diluted and another inflated because its denominator is also contaminated. A common normalization turns the estimator into a mean of ratios whose expectation need not exist; on the same 335 events it returns 0.40 where the well-defined estimator returns 0.10.

arXiv AI Papershace 2 meses

Investigating catastrophic forgetting in sound event classification

This work investigates a number of approaches to prevent catastrophic forgetting in class incremental learning scenarios for sound event classification tasks. We analyze the problem using architectural and regularization approaches, using FSD50K and AudioSet datasets. We design incremental stages and solutions that selectively protect the kernels of the network from weight updates to prevent catastrophic forgetting, and a dynamic head solution that expands itself each time a new task is learned. The findings show that catastrophic forgetting mainly happens in deeper layers, in particular in the classifier head. For the studied in-domain sound classification problem, the solution that seems to alleviate catastrophic forgetting and is the most efficient is a full freezing of the feature extractor with a fine-tuning of the dynamic head classifier, showing little to no forgetting and great training stability, and a good balance between memory-stability and learning plasticity.

arXiv AI Papershace 2 meses

Calibration-Aware Uncertainty Cascades for Efficient Heterogeneous Model Collaboration

Heterogeneous model collaboration seeks to exploit the complementary strengths of different models to balance predictive performance and inference cost. Existing approaches typically rely either on trained routers, which tie routing decisions to a fixed task and model pool, or on raw-confidence cascades, whose thresholds lack consistent reliability semantics across heterogeneous models. Consequently, these approaches adapt poorly to changing model pools and deployment budgets. We propose Calibration-Aware Uncertainty Cascades (CAUC), a simple post-hoc framework that independently calibrates each model's confidence and selects deployment policies using validation data. The resulting calibrated confidence scores establish a common reliability scale for accepting an early prediction, invoking a stronger model, or selectively combining model outputs. This unified decision criterion decouples deployment policies from any particular model pool or operating budget. We further show theoretically that calibration gives confidence thresholds an explicit selective-risk interpretation, whereas uncalibrated scores offer no comparable reliability guarantee. Extensive experiments demonstrate that, across six language benchmarks, CAUC achieves an average relative accuracy improvement of 1.9% over strong-model-only inference while avoiding approximately 47% of strong-model calls. On image classification benchmarks, it maintains or improves predictive performance while reducing measured GFLOPs by up to 57%.

arXiv AI Papershace 2 meses

Hologram Representation via Quadratic Phase Gaussian Splatting

We introduce Complex-Valued Quadratic Phase Gaussian (CVQPG), a novel hologram representation method that replaces standard 2D Gaussian representations used in 2D Gaussian Splatting with 2D quadratic phase functions. CVQPG incorporates additional learnable parameters to control the curvature of these bases. We evaluate our approach against state-of-the-art methods, exceeding the visual quality by +0.19 dB (RGB) and +0.33 dB (grayscale) on average in holographic reconstructions. Specifically, our equal parameter count evaluations show that modulating the primitive's wavefront is an effective and lightweight enhancement for hologram representations. In addition, our frequency domain analysis illustrates that CVQPG has successfully preserved the mid-to-high frequency band of natural images.

arXiv AI Papershace 2 meses

LLMs as Post-hoc Auditors of Physiological Plausibility in Symbolic Regression: A Clinician-Evaluated Case Study

Genetic Programming and its variants, such as grammatical evolution, are widely used in Symbolic Regression to derive mathematical expressions from multivariate data. In addition to predictive accuracy, models are appreciated for their potential to provide interpretability, offering explicit equations that relate input variables to outcomes. However, achieving interpretability and plausibility remains challenging, as evolved models may be complex or scientifically inconsistent. In this study, we explore whether Large Language Models, can assist in improving the explainability of Symbolic Regression models generated by evolutionary computation methods. Building upon our previous work on estimating body fat percentage using grammar-based Genetic Programming , we investigate the use of LLMs as post-processing tools to analyze and rank evolved expressions according to their interpretability and medical plausibility. Four symbolic expressions are analysed by three LLMs over three repeated runs, and the resulting interpretations and rankings are assessed by a panel of three clinicians. Across the three LLMs, comparative model-ranking outputs received more favorable clinician assessments than isolated term-level interpretations. However, the LLMs also produced physiologically and mathematically questionable explanations, indicating that they are better suited to comparative auditing under expert oversight than to autonomous validation.{The present work is an extended version of a paper submitted into a journal.

arXiv AI Papershace 2 meses

SWRouter: Similarity-Contractive Window Routing for Multi-Turn Large Language Model Conversations

Large language models exhibit complementary strengths, motivating routing methods that dispatch each query to the most suitable model. Although existing routers are effective in single-turn settings, they do not directly transfer to multi-turn dialogue, where routing performance critically depends on how historical context is segmented, retained, and incorporated into the current prompt. This introduces two fundamental challenges: preventing information loss and information confusion during context construction, and evaluating routing quality without conflating model selection with prompt construction quality. In this paper, we propose SWRouter, a Similarity-Contractive Window Router for multi-turn large language model routing. SWRouter combines a similarity-based context segmentation mechanism for prompt construction with a dual-metric evaluation framework that decouples construction accuracy from router performance. Experiments on multi-turn dialogue benchmarks demonstrate that SWRouter consistently surpasses strong baselines, achieving a 16.26% improvement in evaluation accuracy over the best individual large language model and an additional 8.22% gain over the Conv-ID Context baseline. Our results highlight that multi-turn large language model routing requires a joint design of context construction and evaluation, rather than a direct extension of single-turn routing methods.

arXiv AI Papershace 2 meses

X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation

Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks perturbs the embeddings consumed by the decoder and can cause deletion and premature end-of-sequence errors. We introduce X-AuT, a progressive framework that selects layer combinations through short behavioral probes and restores the pruned model through representation alignment, cross-scale distillation, scheduled student-policy supervision, and LoRA finetuning. The language-model backbone remains frozen, while attention LoRA adapters and the tied output embedding adapt during distillation. Training uses the highest-agreement tier from a transcript-consistency pipeline, followed by source reweighting during finetuning. On ten public Chinese--English benchmarks, compressing Qwen3-ASR-0.6B from 18 to 16 audio-encoder layers reduces macro-average error from 5.61% to 5.27%. The 14-layer model reaches 5.75% with 20.7% fewer audio-tower parameters. Under the matched recipe, the 1.7B teacher yields 5.55% mean error, compared with 8.45% for self-distillation, and progressive 1814 pruning outperforms direct pruning (5.75% vs. 6.73%). These single-run results establish two practical operating points and show that the accuracy effects vary across benchmarks. Project website: https://xpeng-ai.github.io/x-aut

arXiv AI Papershace 2 meses

Deep-Fake CAPTCHA: Mitigating Next-Generation Social Engineering Attacks

This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and video calls. Instead of passively searching for artifacts, DF-CAPTCHA prompts the caller to perform simple challenge-response tasks that are easy for humans but difficult for current real-time deepfake systems to generate convincingly. The framework verifies the response using four criteria: realism, identity consistency, task completion, and response time. We evaluate the approach across both audio and video modalities using user studies and experiments with real-time deepfake models. Results show that people often struggle to distinguish real-time deepfakes from authentic media, while DF-CAPTCHA substantially improves detection performance over passive methods, reaching high accuracy in both modalities. These findings suggest that active challenge-based verification is a practical and robust defense against next-generation social engineering attacks based on real-time deepfakes.

arXiv AI Papershace 2 meses

From Queries to Narratives: Cultural Heritage Data Stories for Knowledge Graph Exploration and Quality Assessment

Cultural-heritage KGs such as the NFDI4Culture-KG contain millions of triples about artworks, music, inscriptions, historical events, and the people and places connected to them. For many users, however, discovering this knowledge can be difficult. While SPARQL can be learned, writing meaningful queries first requires an in-depth understanding of the graph's data model, an investment many domain researchers and practitioners are unwilling to make. Even with existing user interfaces, a starting point and some guidance are usually needed, because the data contained in the graph is highly specialized, heterogeneous, and constantly growing, making it challenging to know what it contains or which questions it can answer. In this paper, we present data stories as a way not only to lower this barrier, but also to turn exploration into data-quality assessment, and thus combine accessible querying with the discovery of issues that remain hidden in aggregate statistics. In this contribution, a data story is understood as a narrative document that integrates explanatory text and images with executable SPARQL queries and their visualized results. It is described how they are authored against the graph and how they serve several purposes: guiding users through an unfamiliar graph, creating reproducible narratives, and surfacing data-quality issues previously hidden in aggregate statistics. The authoring platform LODEON including its Sparnatural and AI-supported authoring assistants is introduced as a proof-of-concept. Within the authoring environment, every claim made about the data can be backed by an explicit query, making these narratives transparent and reproducible. This paper also reflects on lessons learned from hands-on seminars and workshops. Early experience suggests that such data stories make cultural-heritage knowledge graphs more accessible for both exploration and quality assessment.

arXiv AI Papershace 2 meses

Improving the Sensitivity of Gravitational Wave Detection with Weighted Conformal Prediction

In the last decade, kilometre-scale interferometric gravitational-wave detectors have observed hundreds of compact binary mergers, the majority of which are binary black holes. However, the data are noise-dominated, and multiple independent search algorithms (pipelines) are used to enhance sensitivity and improve robustness. Rather than the standard approach of selecting the most significant pipeline output, we combine the outputs from all pipelines using a conformal prediction-based framework to provide statistically rigorous confidence estimates for candidate events. While combining pipelines improves sensitivity and ranking robustness, it requires a principled statistical framework that remains valid as data properties evolve across observing runs. A key challenge is distribution shifts between simulated datasets used for training and calibration and the real, unlabelled, observations used for testing, which can invalidate coverage guarantees and bias confidence estimates. In this work, we address this challenge by incorporating likelihood-ratio reweighting into our conformal prediction framework to account for covariate shift. Using mock datasets containing simulated signals, we demonstrate that weighted conformal prediction restores well-calibrated coverage under covariate shift and increases the confidence of events near the detection threshold, recovering true signals that would otherwise be missed.

arXiv AI Papershace 2 meses

TransClean: A Benchmark for Detecting and Extracting Clean Translations from Large Language Model Outputs

Large language models (LLMs) are increasingly used for machine translation, yet their outputs often contain additional text beyond the translation itself, such as language labels, explanations or bilingual repetitions, which we term translation noise. Despite its prevalence, this problem lacks dedicated benchmarks and systematic study. We analyze over 790,000 translation outputs from 12 LLMs across 22 language pairs (LPs) and identify 12 recurring noise patterns, which we group into formatting and content noise. Building on the observed patterns, we construct TransClean, a controlled benchmark of 9,900 pairs of noisy and clean translation outputs, comprising 8,800 synthetically generated instances and 1,100 manually curated authentic instances. We evaluate two extraction approaches on the TransClean benchmark: 1) a span-based extraction method leveraging translation quality estimation models for span detection, and 2) an LLM-based extraction method that prompts an LLM to isolate the translation. Our benchmark and analysis provide the first systematic framework to evaluate and improve the cleanliness of LLM translation outputs.

arXiv AI Papershace 2 meses

Beyond Confidence: Stability-Aware Test-Time Adaptation for LLM Reasoning

Test-time adaptation has emerged as a lightweight alternative to costly post-training for improving the reasoning capabilities of Large Language Models (LLMs) on downstream tasks. Predictive entropy provides a model-derived signal for such adaptation, guiding models toward higher-confidence reasoning states without external verifiers or reward models. However, higher confidence does not necessarily imply correctness, as LLMs may remain highly confident along incorrect reasoning trajectories. We observe that high-confidence reasoning is more likely to be correct when confidence remains stable under local perturbations. Based on this observation, we propose Test-Time Adaptation via Stability-Aware Confidence Optimization (TASCO), a framework that incorporates local stability into confidence-based test-time adaptation while keeping the LLM frozen. TASCO operationalizes local stability by optimizing a lightweight task-level prefix under two alternative perturbation strategies: Random Perturbation promotes distributional stability across trajectories induced by nearby perturbed prefixes, whereas Sharpness-Aware Perturbation targets worst-case local sensitivity. Experiments demonstrate that TASCO improves reasoning accuracy and token efficiency across diverse LLMs and reasoning benchmarks, while behavioral analyses show that it maintains stable confidence under local perturbations without prematurely concentrating the model's predictive distribution.

arXiv AI Papershace 2 meses

Buyer Artificial Intelligence-Enabled Environmental Governance and Supplier Environmental Controversies: An Organizational Information Processing and Signaling

Environmental controversies in global supply chains pose significant risks for global buyers. This study examines whether overseas suppliers' exposure to buyers' artificial intelligence (AI)-enabled environmental governance reduces supplier environmental controversies. Drawing on organizational information processing theory and signaling theory, we investigate how suppliers' exposure to AI-enabled governance influences their environmental controversies and the institutional contingencies under which this effect varies. Using text analysis to measure buyer AI-enabled environmental governance, we analyze panel data on 2,505 suppliers of U.S.-listed firms across 41 countries from 2020 to 2024 with multidimensional fixed-effects models. We find that suppliers' exposure to buyer AI-enabled environmental governance is negatively associated with supplier environmental controversies in the following year. This negative relationship is stronger in supplier countries with higher AI readiness and regulatory quality. The study contributes to research on AI-enabled sustainability governance and sustainable supply chain risk management.

arXiv AI Papershace 2 meses

VikingRAG: Accurate and Token-efficient Retrieval-augmented Generation over Structured Documents

State-of-the-art retrieval-augmented generation (RAG) methods exploit document structures to acquire sufficient evidence, but often incur substantial token costs. To reduce structural-context tokens without compromising high RAG accuracy, we present {VikingRAG}, a directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval. To further reduce token overhead of multi-round interaction, we materialize agentic multi-round retrieval traces as experience edges, and reuse these edges for similar queries, avoiding repeated multi-round exploration. To additionally reduce token costs when agentic multi-round retrieval is unnecessary, we introduce an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise. Experiments on real datasets show that the base system {VikingRAG} matches high accuracy of state-of-the-art methods while consuming only 11.6\%--51.9\% of their tokens. With retrieval-trace reuse and adaptive escalation, token costs drop to 5.1\%--32.5\% while maintaining competitive accuracy and practical document-storage performance, showing the utility of this work for emerging AI knowledge bases.