Faced with an unanswerable question, small language models can either refuse or confabulate: confidently produce a wrong answer. Can the hidden state before the first generated token provide a clue? Can we flip confabulations into refusals? I introduce ConfabQA, a 784-item benchmark whose obscure-pre-cutoff category breaks the typical correctness/knowledge-cutoff confound and map the geometry of the hidden state with linear probes, a sparse autoencoder (SAE), and direct optimization of intervention directions. On Qwen3-1.7B and Gemma 2 2B the probe separates upcoming refusals from confabulations well beyond prompt features (+7.4/+16.3 pp); on Llama 3.2 3B the ConfabQA margin is within fold-to-fold spread, but a direct refusal probe on PopQA and TriviaQA recovers +18-25 pp. On Qwen I closely inspect three candidate directions for the refusal vector: probe-recovered, Qwen-Scope SAE feature, and directly optimized. Although the three directions are pairwise 50-81 degrees apart, a push at or below the state's own norm along any of them flips most confabulations into refusal openings dominated by the "As..." family. Forcing the opener without touching the hidden state yields the same one-in-three judged-refusal rate as any push. The opposite push collapses refusals mostly into confabulations, yet leaves originally correct answers intact, so the direction gates the opening speech act rather than the knowledge behind it. Confabulations do not resolve into a concentrated feature in a dictionary or a token signature on Qwen3-1.7B. Scoring every probe on the margin over the strongest of four prompt-feature baselines extracts the hidden state's own contribution. Correctness signal is model-dependent and portable only for Llama 3.2 3B: 81% of the probe's margin over test majority survives transfer between ConfabQA, PopQA, and TriviaQA. Benchmark, judge, and code are released.
https://arxiv.org/abs/2611.01272
Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinct phonology. In this work, we comprehensively evaluate existing zero-shot VC systems for Arabic speech, identifying limitations in pronunciation preservation. We then train an Arabic-centric model based on EZ-VC on diverse Arabic speech, and demonstrate strong performance in intelligibility, naturalness, and pronunciation preservation, while maintaining high speaker dissimilarity. Through subjective evaluation, we further demonstrate its robustness to code-switching and cross-dialectal conversion, as well as its generalization to Arabic dialects with limited representation in the training data. Our findings highlight the limitations of zero-shot VC and the importance of target-language adaptation for robust voice anonymization.
https://arxiv.org/abs/2611.01268
Pretrained models are typically viewed as generalists, requiring bespoke post-training to achieve task-specific expertise. Gan & Isola (2026) recently proposed a striking alternative: that pretrained models lie in a dense neural thicket of task specialists, which can be surfaced with simple Gaussian weight perturbations. We examine this neural thicket of task-specific experts and identify several key findings that question this perspective. First, we find that the apparent lift of the best-of-N selected perturbation decays quickly with selection-set size m, strongly suggesting overfitting to the selection questions. In fact, for 10 of the 12 model-task pairs we study, a simple null model of pure selection noise predicts more than 75 percent of the top expert's reward lift. Second, the top experts' advantage often vanishes on held-out questions or remains within the run-to-run variability of the unperturbed pretrained model. Third, we find that majority voting over the top-K selected perturbations, termed RandOpt(N, K) by Gan & Isola (2026), is often matched or outperformed by majority voting over K samples from the base model. Overall, our results suggest that random weight perturbations may be ineffective at uncovering task experts around pretrained models, and that task adaptation requires more sophistication than random search. Code and artifacts are available at this http URL.
https://arxiv.org/abs/2611.01262
Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval. We present MedAstra, a framework that maps frozen WavLM speech representations through a lightweight adapter into a frozen E5 text embedding space. This enables a dense retrieval path that accepts a waveform without a query transcript. Retrieved passages and speech-linked textual metadata support answer generation with entity alternatives, diagnostic contrasts, relation heuristics, and bounded retrieval refinement. ASR-less refers to the initial speech retrieval interface; lexical retrieval, string-based entity correction, and the text generator require textual inputs. The deterministic speech embedding does not constitute a calibrated model of acoustic uncertainty. Reported retrieval results reach 87.6 Recall@10 for the speech-only retriever and 90.4 for the hybrid configuration, compared with 81.0 for transcript-first dense retrieval. Medical QA and ablations provide descriptive system comparisons, with input-provenance and evaluation limitations stated explicitly. We distinguish controlled synthetic acoustic tests from real clinical speech, qualify component attribution, and specify the remaining comparisons needed to assess speech-only QA and clinical generalization.
https://arxiv.org/abs/2611.01261
In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location term extraction. Our results demonstrate that native (Slovak) prompts yield a modest, task-dependent gains, while large models show significant robustness to prompt variations compared to their smaller counterparts. Analysis reveals that instructions (system or task) emerge as the most critical prompt component, more so than the examples sections, with task-specific performance benefits being more pronounced than overall language effects.
https://arxiv.org/abs/2611.01219
In the online unweighted knapsack problem, items arrive sequentially and must be accepted or rejected immediately for a bounded-capacity knapsack, aiming to maximize the total size of accepted items. When decisions are irrevocable, no algorithm achieves a non-trivial competitive ratio. An essential relaxation that circumvents this impossibility is to allow previously accepted items to be removed from the knapsack (a.k.a. removal). In this work, we investigate possible further improvements on the competitive ratio with removal by bringing together two other previously proposed model extensions: knowledge of an upper bound on the item sizes (a.k.a. bound awareness) and ability to reinsert previously rejected items(this http URL). Our contributions are twofold. First, we establish close upper and lower bounds on the competitive ratio under bound awareness, removal and recourse. We show that significant improvements on the best known competitive ratio are possible when the upper bound on the item sizes is not too restrictive and only few uses of recourse are available. Second, we introduce the notion of adaptive online algorithms which do not require to know any upper bound on the item sizes but still achieve performance guarantees comparable to the ones obtained under the bound awareness model.
https://arxiv.org/abs/2610.40290
Despite growing interest in Arabic natural language processing, curriculum-aligned educational resources remain scarce compared with English, and few public datasets for Arabic curriculum content with structured, generation-ready annotations are available, particularly for primary-school science. We introduce ArSciKids, a collection of two Arabic datasets designed for curriculum-aligned educational content generation: (1) a scientific-experiments dataset containing 999 manually curated records from official primary-school science textbooks in Saudi Arabia, Syria, and Jordan, and (2) an assessment-question dataset containing 2,167 multiple-choice questions collected from the Saudi Manhaji educational platform. The experiment records are structured with titles, objectives, tools, procedures, observations, conclusions, keywords, and grade levels, while the assessment records contain lesson references, questions, four answer options, correct answers, and explanations. Both datasets cover grades 1-6 and consist of real-life Arabic educational content rather than machine-translated or synthetically generated material. We assess the usefulness of these resources for generation by fine-tuning ten open models spanning sub-billion to several-billion parameter scales using LoRA. Models are evaluated using automatic metrics, including ROUGE and BLEU, and answer accuracy for multiple-choice generation. Moreover, we evaluate the results using a five-criterion human evaluation protocol. The results show substantial differences across model scales and tasks. ArSciKids will be publicly available, and we hope that it provides a manually curated, structured foundation for research on Arabic educational NLP, curriculum-aware generation, and low-resource language modeling.
https://arxiv.org/abs/2611.01191
Novelty in solution generation supports automated discovery, but LLM outputs can remain repetitive. To address this, we propose a simple concept-guided prompting method that generates thematic concepts before responses within each of these concepts. To demonstrate, we generated 1,000 recipes for a recipe book task and compared the results against a human-authored corpus. Two naive prompting strategies were compared as baselines. Concept-guided prompting outperformed both baselines in all cases and reached semantic coverage of 47.0% versus 35.1% and 13.1% in respective prior-title and nonce prompt strategies. These findings suggest broader population exploration and diversity, but remain contained to this specific task. Further work is needed to determine the quality of solutions and generalizability.
https://arxiv.org/abs/2611.01171
Generative spoken language models (SLMs) offer a route to learning linguistic structure purely from speech, yet they lag far behind text-based models in both capability and data scaling efficiency. We identify two bottlenecks underlying this gap: the limited linguistic quality of existing speech units and the reliance on a single stream of discrete units to represent speech. Multiple codebooks are widely used to encode acoustic features but rarely to represent speech semantics. We present GSLM2, which learns and models complementary properties of speech at multiple levels of abstraction. Its encoder, SpidR 2.0, uses self-supervised learning with differentiable prediction heads to induce high-quality discrete units at multiple levels. A multi-stream SLM then jointly models these units using a shared temporal backbone, stream-specific predictors, and an autoregressive head that captures cross-stream dependencies. Across training data sizes and model scales, up to 6M hours and 6.5B parameters, GSLM2 consistently improves linguistic competence while scaling more efficiently with data. As a result, it substantially narrows the gap between spoken and text-based LMs; across read and conversational speech domains, we shrink the gap by about two orders of magnitude on sWuggy, sBLIMP, and tSC, while also outperforming competitive speech-text systems on all three tasks. We open-source the training code and model checkpoints at this https URL.
https://arxiv.org/abs/2611.01143
Structured pruning reduces the size of large language models, often at the cost of lower accuracy. Whether this decline reflects diminished reasoning capacity or greater difficulty in sampling correct solutions is less clear. We examine this question across expert, FFN and layer pruning on four mathematical and coding benchmarks, comparing original and pruned models through pass@k at matched sampling budgets. Even after substantial pruning, some models match or exceed the original model's reasoning coverage despite lower pass@1, and solve problems left unsolved in the original samples. Retaining broad coverage, however, does not mean that correct solutions remain easy to obtain. Under severe pruning, diverse generated chain-of-thought (CoT) traces can coexist with increased repetition and less reliable generation. As correct answers become harder to sample, the additional attempts can sharply increase total token use even when individual responses become shorter. This separation between coverage and sampling efficiency also clarifies expert-selection gains, as methods with markedly different pass@1 can solve the same problems at large budgets yet require different numbers of attempts to reach a common coverage target. Pruning should therefore be assessed by both the range of problems a model can still solve and the sampling cost of obtaining correct solutions.
https://arxiv.org/abs/2611.01133
Financial restatements correct errors in previously published financial reports. Could managers' language in earnings calls warn of them in advance? Comparing 109 calls that precede restatements with 218 matched control calls, we find that the text predicts restatements but adds no detectable ranking gain beyond public firm information. A text classifier beats chance, largely because of restatements tied to special-purpose acquisition companies, but a model using only public information scores slightly higher. With refitting, the 95% interval for the gain from adding text (-0.05 to 0.11 AUROC) still leaves room for a meaningful benefit. A large language model scores higher, but we show that it names the exact ticker in 66% of masked transcripts, and it was released after the restatements occurred. Our results suggest that finding new warning signs in call text requires a public-information baseline and a check of what a language model already knows.
https://arxiv.org/abs/2611.01123
LLM agents increasingly rely on skill documents, yet most retrievers rank them by description alone and ignore what earlier executions revealed, even though a relevant skill can hurt execution. We present CompSkill, which indexes skills with learned 512-d keys and compiles matched same-task comparisons into skill offsets and capped key residuals (KeyOpt), so experience changes which document the executor receives, never its text. Under a logistic outcome model with unknown task difficulty, matched comparisons cancel that difficulty and only discordant ones carry information; on support executions, predictions improve with each discordant task. An experience hypergraph keeps each comparison with its executor and document versions, recalls missed skills and grounds a cited review. Compact keys raise SkillRet NDCG@10 from 64.0 to 70.9 at one eighth of the dimension. With one document, CompSkill completes 256 and 260 of 332 ToolQA tasks with GPT-5.6-luna and DeepSeek-V4.1-Flash, respectively, more than every baseline, and stays on par with the strongest baselines on AppWorld and ALFWorld. On 332 newly generated ToolQA tasks, it completes 256 with GPT-5.6-luna, significantly more than BM25, SkillRet-8B, Tool2Vec and RankGPT; over all 844 ToolQA tasks, it completes 24 more than the strongest baseline. Selection matters beyond relevance: pairing the right guide with a same-database sibling instead of another database's guide costs 8 of 96 tasks. Code, models and support data: this https URL
https://arxiv.org/abs/2611.01115
Can a language model learn better ways to reason about other people's minds by improving its own strategies, and are the strategies it learns actually right? We study this with cogrsi. A grounded reader marks who saw each event in a story and uses a short written principle to settle disagreements between its readings. With a principle written by experts, it beats self-consistency at the same token cost. A self-improvement loop then writes the principle itself. It keeps an update only if accuracy rises by a calibrated margin, and in one variant only if it also passes counterfactual test pairs. The learned principles transfer: on 800 BigToM pairs that no system had seen, each of them scores higher than the expert principle. We then check what the learned rules actually say. Each rule is translated into code and run on thousands of small stories with known answers. Most of them give a wrong answer in at least one situation they claim to cover, for example by treating a character who is in the room as knowing what happened even while asleep. Accuracy does not reveal which rules are wrong, and the counterfactual test does not fix this. A strategy can help in practice and still be wrong as a rule, so both need checking. Our code and data are publicly available.
https://arxiv.org/abs/2611.01113
Semantic caching lowers the cost of serving large language models (LLMs) by reusing stored responses for similar requests. In multi-turn conversations, whether a cached response is acceptable depends on both conversations' histories, which embedding similarity of requests and histories predicts poorly (AUC 0.62--0.74 on five workloads). We therefore learn the \emph{reuse risk}, the probability that a cached response is unacceptable, from judge feedback, and choose a budgeted set of conversation states to cache by weighing the generation cost a reuse avoids against a price for unacceptable reuse. We propose CUCB-SC-MT, which learns a cache from logged conversations with a suboptimality guarantee, and CLCB-LS-MT, which learns online and has $\tilde O(\sqrt N)$ regret over $N$ requests when conversation states recur. On math-tutoring (SocraTeach) and movie-ticketing (Taskmaster-3) conversations, both achieve lower loss than prior semantic caching approaches: ContextCache, multi-turn variants of ElastiCache and vCache, and single-turn semantic caching at every cache budget. With 1,000 cache entries, CLCB-LS-MT avoids 35--41\% of the generation cost through acceptable reuses, against at most 22--25\% for the baselines, and lowers estimated serving latency by 19--35\%.
https://arxiv.org/abs/2611.01077
Gated knowledge distillation (KD) weights teacher signals per token or example, aiming to trust an imperfect teacher only where it seems reliable. We test two gates: EWAD (entropy-weighted agreement-aware distillation), which gates tokens by teacher confidence, and CHAD (counterfactual harm-aware distillation), which gates examples by gradient alignment with validation data. Across six Bangla-centric tasks, three student models (60M to about 2B parameters), and two teacher families, no gate significantly improves plain KD in 45 comparisons. KD also fails to beat cross-entropy (CE) fine-tuning on gold outputs in 40 single-seed comparisons or three-seed runs on four tasks; CE leads on every summarisation metric. The main benefit of KD is regularisation: over ten fixed epochs, CE students lose 0.030 to 0.044 token-F1 from their early-stopped checkpoint, versus 0.005 to 0.025 for distilled students. Teacher-free label smoothing closes most of this gap. In one comparison, a teacher 0.29 token-F1 worse yields students at most 0.009 worse. Thus, gating may change regularisation strength but has little teacher knowledge to select. Findings are limited to Bangla-centric tasks and small students. We will release code, data splits, predictions, and scores.
https://arxiv.org/abs/2611.01065
Learning from extensive longitudinal clinical records--spanning repeated encounters, evolving conditions, and heterogeneous documentation--under a finite labeling budget requires solving two coupled problems: deciding what evidence to keep and deciding which patients deserve higher-fidelity labels. Prior work on active learning and multi-fidelity label acquisition mainly addresses the second problem, while treating the evidence presented to the acquisition policy as fixed. We present HALO, a Hierarchical Evidence Selection and Reinforcement Learning pipeline for Allocating Budgeted Label Optimization from Longitudinal Clinical Records. This framework jointly learns what to read and what label source to acquire under budget. HALO first selects informative evidence from longitudinal records and then uses a budget-aware policy to allocate free-, silver-, and gold-fidelity label sources. For frozen policies, our theory characterizes asymmetric acquired-label channels and gives a budget-constrained finite-sample gold-risk bound for a common downstream logistic model. In a heart-failure case study, HALO attained the highest MedAlign acquired-label F1 at six of eight target budgets. A downstream classifier trained on HALO-acquired labels attained the highest external MGB F1 at budgets 15-60 and remained within 0.01 of the best comparator at budgets 75-120.
https://arxiv.org/abs/2611.00986
Early-exit language models decide for each token how much computation to spend, usually by stopping once the prediction is confident. Yet a token is not a fixed unit: tokenizers cut words into different numbers of pieces in different languages. We ask where inside a word such a policy spends its budget. In Qwen3, along two adaptive axes (the timesteps of a spiking conversion and the layers of the original Transformer), confidence stopping gives the continuation pieces of a word less computation than its first piece in English, German, and Turkish, but more in Bangla. Segmentation drives this. Re-segmenting the same parallel passages with BPE-dropout shifts the gap by up to eight exits on both axes, small models trained under two tokenizers shift Bangla's gap by six exits, and BLOOM and mGPT, which split Bangla less finely, give it the English pattern. Characters per token do not predict the gap across languages; within-word surprisal explains 75% of its variance. A learned stopping head beats confidence stopping by 7 to 8 points, but gains less than one point over the best mix of fixed exits at equal cost, and sometimes loses. All results come from offline analysis, not measured speedups.
https://arxiv.org/abs/2611.00983
Text-to-SQL assistants for streaming engines must handle dialect-specific types, windowing rules, and temporal semantics, including constructs poorly handled by generic prompts. We present Self-Refining Prompt Induction (SRPI), an offline method that converts generation failures into reusable dialect instructions while keeping model weights fixed. A Refiner revises the Generator's prompt using reference-conditioned feedback from three LLM judges; a sampled regression guard checks earlier successes, and a separate Compressor reduces prompt length. Inference uses the frozen prompt without retrieval or query repair. We evaluate cross-domain and cross-model transfer on Confluent Cloud Flink SQL using a controlled synthetic workload seeded by 30 expert-written examples, with 335 induction examples and 257 questions from held-out domains. The same induced prompt improves mean judge scores across seven Generators by 7.1-19.2 percentage points, including an increase from 85.3% to 97.5% for the induction model. A separate compression study reduces prompt length by 52.7% with a 0.19-percentage-point score decrease. An assistant using the induced prompt is in early access, with initial user feedback to inform subsequent refinement.
https://arxiv.org/abs/2611.00960
Bock's algorithm provides a matrix-based alternative to Chu--Liu/Edmonds (CL/E) for exact dependency parsing. We present a reformulation that retains original node and arc identities through component labels, column adjustments, and star-and-bar transfers. In exact arithmetic, we prove operational equivalence to original Bock under matching scan and tie rules, and establish correspondence with corrected Tarjan under a prescribed component schedule. A separate analysis establishes optimal-value equivalence with Dozat-derived CL/E under the stated score and single-root conventions. We integrate reformulated Bock into a biaffine dependency parser and evaluate decoding and structured training on the Penn Treebank and Chinese Treebank. These results establish Bock as an alternative exact oracle for dependency parsing and structured training, while distinguishing equality of optimal values from identity of returned trees and training trajectories.
https://arxiv.org/abs/2611.00939
Advances in large language models (LLMs) have created opportunities for cross-lingual transfer of medical knowledge from high-resource to low-resource languages to support access to healthcare information. However, medical question-answering (QA) datasets for fine-tuning and evaluating LLMs remain scarce for Tetun. To address this gap, we translated MedAlpaca's Medical Flashcards and WikiDoc Patient Information collections into Tetun using Gemini 2.5 Flash, producing 39,077 medical QA pairs. Translation quality was assessed on 50 randomly sampled QA pairs (100 documents) using automatic metrics against human reference translations and evaluations by two native Tetun-speaking healthcare professionals, focusing on medical accuracy and Tetun fluency. Human translations achieved higher mean ratings than LLM-generated translations for both criteria (4.43/5 vs. 4.02/5), with statistically significant differences (Wilcoxon signed-rank test, p < 0.001). To assess downstream utility, we fine-tuned Gemma and Llama variants on the translated MedAlpaca dataset using parameter-efficient fine-tuning (PEFT) and evaluated them on 325 Tetun-translated United States Medical Licensing Examination multiple-choice questions. Gemma 4 12B fine-tuned using QLoRA achieved relative improvements in mean accuracy of 10.79% with 4-bit NormalFloat (NF4) inference and 10.42% after merging the LoRA adapters into the BF16 base model, compared with the corresponding base models. These results highlight the viability of automatic dataset translation for Tetun medical QA and the effectiveness of PEFT in enhancing model performance. The datasets, models, and evaluation resources are accessible at this https URL to support reproducible research on Tetun medical QA and facilitate machine translation, cross lingual, and multilingual research.
https://arxiv.org/abs/2611.00935