arXiv:2610.29110v1 Announce Type: new Abstract: Merging different models into a single model is highly desirable for multi-task deployment, particularly in regulated domains like healthcare. In such settings, models are often locally fine-tuned due to strict data privacy policies, necessitating that aggregation operates exclusively on the fine-tuned weights. Existing methods apply a uniform merge across all tasks, ignoring the geometric relationships among their learned subspaces. When task upda
arXiv:2610.29121v1 Announce Type: new Abstract: A coding agent that rewrites its own scaffold has to choose which proposed edit to expand before that edit has been evaluated, and the search then has to return one agent. Each run fits one linear readout on the parent's steering-split solve rate and eight coordinates of the proposed diff, from 96 scaffold edits labeled by four evaluations of a 16-instance fit split, and then freezes the coefficients. HumanEval+ reserves 48 instances as the steerin
arXiv:2610.29122v1 Announce Type: new Abstract: Individual patient data are the gold standard for secondary analysis of time-to-event evidence, but they are rarely released, and reconstruction from a published Kaplan-Meier figure could help. Existing methods all claim high fidelity, each judged by whichever agreements it happens to achieve, and each returns a single dataset although the map from figure to data is not bijective. We define fidelity explicitly: a dataset is admissible when it repro
arXiv:2610.26864v1 Announce Type: new Abstract: Gradient ascent (GA) is a simple language-model unlearning baseline, but it continues increasing forget loss after useful forgetting has occurred. This unbounded pressure can damage retained utility and make forgotten examples abnormally high-loss. We introduce H2DF, a calibrated target-band objective that applies GA-like pressure below a data-dependent lower target and suppresses, or reverses, that pressure after the target region is reached. The
arXiv:2610.26865v1 Announce Type: new Abstract: Retrieval-augmented speech translation improves rare terminology, but systems such as RASST still assume that users provide a glossary before each session. That assumption is inconvenient for live talks, while merging every domain into one growing glossary eventually places too many irrelevant terms in the same retrieval and prompt competition. We present AutoTerm-SST, an interactive system that removes session-time glossary upload and domain selec
arXiv:2610.26867v2 Announce Type: new Abstract: Modern speech systems are evolving into ecosystems of autonomous speech agents that interact, negotiate, and trade assets such as embeddings, spectrograms, or raw data. In such markets, sellers cannot reveal assets for evaluation due to privacy constraints, and buyers cannot price what they cannot test. Thus, we introduce WaveCommitments, an end-to-end design that couples multivariate polynomial commitments with confidential asset valuation via Dat
arXiv:2610.26868v1 Announce Type: new Abstract: Ambivalence and hesitancy (A/H) are subtle behavioural states that can be expressed through both what a person says and how it is spoken. This paper presents an audio--text framework for video-level A/H recognition. Full-video transcripts and speech waveforms are encoded using pre-trained multilingual BERT and wav2vec~2.0, respectively, and projected into a shared representation space. Two stacked bidirectional cross-attention blocks allow linguist
arXiv:2610.26888v1 Announce Type: new Abstract: We present Mixture of Phonetic Experts based Low-Rank Adaptation (MoPE-LoRA), a parameter-efficient adaptation framework for accented English speech recognition. Recent mixture-of-experts approaches typically allocate experts per accent, implicitly treating accent identity as the primary axis of variation. In contrast, we organize adaptation along phonetic categories, motivated by the observation that accent differences are often expressed as syste
arXiv:2610.26926v1 Announce Type: new Abstract: Large language models (LLMs) possess broad factual knowledge and strong reasoning capabilities, but solving complex tasks also requires procedural knowledge about how to act. Existing approaches often represent procedural knowledge through trajectories or bundled skills, limiting flexible reuse across interaction histories. This paper introduces Procedural Atoms, fine-grained and independently applicable units that represent Intent, When, Do, and A
arXiv:2610.26937v1 Announce Type: new Abstract: Large clinical language models often require multi-GPU infrastructure, limiting local deployment. We introduce CERTA, a decision-level statistical certificate that determines when a quantized model may substitute for its native BF16 reference and escalates decisions that cannot be certified to it. Across eleven instruction-tuned models, both general-purpose and domain-adapted, from three families (7-72B), we evaluated 2,500 clinical-verification de
arXiv:2610.26951v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) is the dominant paradigm for grounding large language models in external corpora, but its similarity-driven, chunked pipeline has structural blind spots: it cannot anticipate which passages a question requires and discards document-level context that resolves cross-passage references. We introduce evidence-based generation (EBG), requiring models to return an answer with line-level citations, and a joint Ans+Evi
arXiv:2610.26952v1 Announce Type: new Abstract: Relational triple extraction identifies entity relations from raw sentences without depending on entity type information. The performance of traditional methods is seriously degenerated by ``unseen'' entities, because these methods can't build contextual dependencies relevant ``unseen'' entities. This paper addresses this challenge by proposing a multi-granularity interaction network that leverages word-word, entity-relation, and head-tail interact
arXiv:2610.26955v1 Announce Type: new Abstract: Long-horizon language agents require compact memories that retain interaction evidence while preserving competing hypotheses about unobserved states. Although effective, many belief-state methods encode memory in discrete natural language, where repeated compression can omit evidence or prematurely discard plausible alternatives. We introduce LAMB, a recurrent framework for latent multi-hypothesis beliefs. A Common--Delta factorization combines a s
arXiv:2610.26972v1 Announce Type: new Abstract: We present SZED's submission to ArGuard 2026 Track A: Arabic hateful meme detection. The task has two parts: binary classification (A1) and fine-grained multi-label tagging (A2). For A1, we fuse MARBERTv2 and CLIP ViT-L/14 embeddings, comparing concatenation, self-attention, and ensemble heads. For A2, we use a multi-task label-attention architecture with per-class query vectors and an auxiliary head for cascade calibration. We reach macro-F1 = 0.7
arXiv:2610.26976v1 Announce Type: new Abstract: We establish sharp degree bounds for Putinar sum-of-squares (SOS) certificates in terms of the positivity margin $\delta$. For any fixed Archimedean quadratic module with prescribed generators and any fixed bound on the degree of the objective, we prove a uniform certificate-degree upper bound of $O(\delta^{-1/2}\log^2(2/\delta))$ for normalized polynomial objectives. We show that this bound is sharp by constructing a matching lower-bound example i
arXiv:2610.26986v1 Announce Type: new Abstract: Contextual automatic speech recognition (ASR) improves rare-entity recognition by supplying candidate hotwords, but retrieved candidates may be incomplete or incorrect. A reliable system must therefore exploit a relevant candidate without allowing unsupported alternatives to override the acoustic evidence. We propose a context-steered reasoning framework that generates a short, audio-grounded caption before transcription. This task-specific represe
arXiv:2610.26993v1 Announce Type: new Abstract: Existing benchmarks for text-vision embedding models report aggregate scores that obscure whether performance comes from general capabilities, task-specific adaptation, or robustness to challenging tasks. We introduce TRACE, a Training-aware Robustness and Challenge Evaluation framework that reorganizes 168 tasks from various sources of datasets into three categories: General, Adaptability, and Challenge. Through controlled experiments on two text-
arXiv:2610.26994v1 Announce Type: new Abstract: Activation steering for ASR systems is an underexplored technique in improving both ASR performance and demographic fairness. We investigate two forms of activation steering: paired activation subtraction, and supervised optimization. We find the former to be ineffective at ameliorating ASR performance whatsoever, while the latter is quite effective at deriving steering vectors (SVs) that improve at once overall ASR performance and demographic fair
arXiv:2610.27002v1 Announce Type: new Abstract: Tibetan speech recognition is usually evaluated with character or syllable error rates because the writing system does not mark word boundaries. These metrics can rank systems differently and respond differently to adaptation failures. We combine character error rate, syllable error rate, and segmented word error rate in one evaluation framework. We use dictionary-based, neural, and language-model-based segmentation and compare their boundaries wit
arXiv:2610.27013v1 Announce Type: new Abstract: Relation extraction from aviation accident narratives is challenging because genuine safety relations are sparse among possible concept pairs. This study evaluates a decomposed framework separating relation classification from concept identification. A benchmark of 300 National Transportation Safety Board (NTSB) narratives containing 2,524 unique concept-text nodes was expanded into 21,038 ordered candidate pairs, with only 248 (1.18%) representing
arXiv:2610.27034v1 Announce Type: new Abstract: Large Language Models (LLMs) have significantly advanced natural language processing and artificial intelligence applications through their capabilities in reasoning, text generation and knowledge retrieval. However, LLMs are still vulnerable to two important challenges: hallucination, generating factually incorrect or fabricated content, and response deviation, meaning systematic deviations from ground-truth responses. These limitations raise seri
arXiv:2610.27043v1 Announce Type: new Abstract: Financial institutions increasingly deploy large language models (LLMs) in multilingual markets, raising a practical question: can pipelines developed and validated in English be reused across languages, or must they be rebuilt per locale? We test cross-lingual reusability along three dimensions--accuracy, reasoning-effort transfer, and behavioural stability--through three complementary tasks. Task 1 (cheque extraction) and Task 2 (Mintaka QA with
arXiv:2610.27047v1 Announce Type: new Abstract: EHR foundation models promise scalable clinical prediction across health systems, yet their deployment is constrained by a tokenization bottleneck. The same clinical concept can appear as different ontology codes, local identifiers, synonyms, or free-text descriptions, which standard EHR tokenizers treat as unrelated symbols. A model trained on MIMIC-III with a closed-vocabulary tokenizer can use only 13% of eICU events. We introduce MEDIATOR, a di
arXiv:2610.27114v1 Announce Type: new Abstract: Retrieval-augmented QA can fail even when the correct answer is in the retrieved evidence. This can happen when a competing answer satisfies some, but not all, of the question's requirements and is mentioned frequently in the retrieved documents, which can make it appear to be the best-supported answer. To test whether this retrieval skew actually affects the decision, we manipulate it directly: increasing the prevalence of passages that favor the
arXiv:2610.27142v1 Announce Type: new Abstract: Data selection plays a central role in modern large language model training, as the quality of training data strongly influences downstream performance. A common approach is to curate a development set that encodes the desired skills (e.g., reasoning or multilinguality) and select data that are similar to them. Existing methods compute similarity using cosine distance over either the model's hidden states or gradients. However, we observe that this
arXiv:2610.27149v1 Announce Type: new Abstract: Health-related discussions on social media are increasingly shaped by influencers who offer diverse, and often competing perspectives on the same issue. Yet, such content is typically evaluated in isolation, without considering the broader discourse in which it appears. We introduce GRID (Grounded Reasoning over Interconnected Discourse), a framework for evaluating influencer content through collective inference over the surrounding discourse. GRID
arXiv:2610.27178v1 Announce Type: new Abstract: Platforms that host young users screen messages with commercial text-safety APIs, but independent evidence on how often such systems miss harm or flag harmless text is scarce, especially outside English, and the documentation of the one studied here leaves its false-positive rate unquantified. We evaluated one such API, Tuteliq Detect as deployed under the release identifier tuteliq-detect-v5.20261011 (not the separately published v6 model), on six