Pharmaceutical sponsors developing a drug for both the United States and the European Union must reconcile guidance issued independently by the FDA and the EMA. Where the two agencies require substantively the same thing, a sponsor can file once; where they diverge, a single trial design risks rejection in one region; where one agency is silent on a point the other regulates, the sponsor must infer obligations. Today this reconciliation is performed manually by regulatory-affairs experts. We introduce cross-jurisdiction regulatory divergence detection: given an FDA requirement and an EMA requirement on the same topic, classify their relationship as AGREE, DIVERGE, or SILENT. SILENT is inherently directional (SILENT_FDA vs. SILENT_EMA); we record direction per pair and report per-direction F1 alongside the collapsed label. We release RegDivergence-101, a 101-pair expert-grounded pilot evaluation benchmark (labels grounded in three peer-reviewed FDA/EMA comparison studies and primary FDA/EMA/ICH guidance text; dual-annotation inter-annotator kappa = 0.85), and systematically characterise a four-method baseline hierarchy: lexical heuristic (0.511 macro-F1, 95% CI [0.411-0.605]), NLI cross-encoder (0.233), obligation-level Graph-RAG (0.663 [0.570-0.747]), and flat LLM judge / Claude Haiku (0.830 [0.747-0.908]). Three directional observations emerge at pilot scale (n = 101): SILENT is semantically detectable but invisible to entailment-only formulations; pair-level obligation graphs improve over lexical methods but trail flat-LLM context (CIs partially overlapping); and corpus-level graph construction is the indicated architectural target for large-scale silent-detection. RegDivergence-101 is a pilot release establishing the task formulation and baseline hierarchy; four unrepresented regulatory domains and an expansion roadmap are described in Section 7.
Chuchu Wu, Zhiyin Zhou, Jingzhuo Hu et al.· 0 citations
Ambient AI scribes draft clinical notes under the reassurance that a clinician signs every note. We audited three commercial AI scribes on the same 142 consultations: 565 notes from recorded UK primary-care and US ambulatory encounters plus authored scenarios. Twelve discovery passes proposed 13,678 candidate errors; the 5,898 clearing an importance filter went to an adversarial panel of two models from different families, each told to refute what it could, and 618 survived. One note in three (31.3% [27.0, 35.6]) carries a verified failure, concentrated in allergy and medication information, invented patient identity, and history written up as examination on telephone consultations that can contain none. No product was given a patient record; setting aside the two classes a record would have prefilled, invented identity and dates, the rate is 24.8% [20.8, 29.0]. One failure mode did not fit our scheme, drawn from published scribe-error taxonomies: a treatment the clinician retracts, recorded as delivered care. Two clinicians adjudicated blind, disjoint samples: a physician author upheld 20 of 21 findings (95.2% [77.3, 99.2]) and an independent clinician, not an author, 12 of 12 ([75.8, 100]); both judged every sampled refusal genuine. A failure rate depends on the instrument as much as the scribes. With model, evidence and settings fixed, the review instruction alone moves the share of candidates verified from 9.3% to 79.0%, and the reviewing family moves it too: alone at that instruction the gentler flags 54.8% of notes against 27.8%. Between 28% and 97% of sampled notes carry a failure depending on the standard. Published audits disagree among themselves by a margin instrument differences alone can produce: omission is 54-86% of their errors against our 23.1%. We release all 618 findings with transcript-side evidence, every prompt and model version, and the re-runnable pipeline.
Sebastian Fox, Luke Markham, Ryan Lail et al.· 0 citations
Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the note fails to record. The standard check is an LLM judge: a second model reads the note against the transcript and flags problems. We ask whether judges detect omissions. Public corpora cannot supply the answer key: their clinician reference notes and transcripts are materially discrepant. Our benchmark has 500 single-error note pairs from audited fact sheets, 298 with a named fact certainly absent and 202 added-or-altered controls. Across eight judge designs, paired discrimination (the flawed note below its clean twin, 0.5 a coin flip) reads 0.79-0.94 on added or altered content and 0.50-0.63 on omissions. On single notes, no design flags omissions reliably more often than perfect notes. Wording changes, voting and GEPA prompt optimisation move the operating point without creating usable detection. Restructuring the task recovers it: list the facts the transcript establishes, then check the note for each. Two methods reach it independently and trade off: a per-fact pipeline, and a GEPA-evolved prompt doing the same in one call. The pipeline's flags name the missing fact and its severity at 2.7% false alarms. The single call detects more (36.9% against 24.6%, p=0.002) at 6.2% false alarms and a tenth of the cost per note. A physician author validated 70 items and, where the two routes disagree, sided with the pipeline on 10 of 10 (p=0.002). A second clinician, not an author, graded the severity rubric blind and agrees to within a grade. On real vendor notes from a companion census no benchmark threshold transfers, but the re-calibrated single call detects more than the best of the eight at half its false-alarm rate. Omissions whose fact is restated elsewhere defeat both routes. We release the benchmark, prompts and judgements.
Sebastian Fox, Luke Markham, Ryan Lail et al.· 0 citations
We study self-modeling: an LLM's ability to answer questions about its own behavior. We focus on verifiable behavioral questions, such as whether a prompt edit would change the model's final answer. To measure this capability, we introduce a benchmark that tests diverse types of self-modeling questions. Current models show non-trivial but limited self-modeling skill, and make systematic mistakes on simple counterfactual questions about their own behavior. To improve self-modeling skill, we develop a scalable synthetic-data pipeline that produces self-modeling training data, and show that reinforcement-learning can improve aggregate self-modeling skill across three open-source model families with some transfer to held-out tasks. These gains, however, do not seem to constitute introspection consistently: improved self-modeling may not arise from privileged access to the model's internal decision process.
Siqi Zeng, Andre N. Assis, Rowan Wang· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
We present CogEvol, a family of models trained specifically for Learning Environment Generation: turning a course brief into a finished learning artifact (structured-JSON slides or self-contained interactive HTML pages) in a single pass. Across 220k production requests, CogEvol completes a slide in a median of 17 seconds and an interactive page in 59, replacing minutes-long multi-turn agent scaffolding. Reliability is enforced rather than hoped for: a production-grounded data pipeline turns real failures into 53,687 verified SFT samples, and a hybrid rule-plus-VLM reward drives GRPO-based RL, hardened after we caught and fixed a reward-hacking episode that produced visually convincing but unplayable games. CogEvol-27B scores 83.7 on slide quality and 63.7 on a 500-case interactive-HTML benchmark with 26.9x fewer parameters than flagship coding models, and, in collaboration with the OpenMAIC team, serves their live production traffic. CogEvol-4B is released openly under the Apache 2.0 license at https://github.com/CogEvol/CogEvol-4B; external flagships are measured on the same suites under the identical harness. Scaffold editing cuts interactive-page generation cost by a further ~76%, and the full stack runs on domestic Ascend accelerators at application-level parity with A800 GPUs, lowering the unit cost of AI-native education at scale.
Shangqing Tu, Daniel Zhang-Li, Yucheng Wang et al.· 0 citations
While gender and racial biases in language models have been widely studied, anti-LGBTQ biases remain underexplored, particularly beyond English. Existing benchmarks often do not capture cultural and linguistic variation and rely on gender representations. This paper introduces a multilingual German-English benchmark dataset for the evaluation of anti-LGBTQ biases in language models. It combines community-sourced stereotypes from German-speaking queer individuals with a German translation of WinoQueer. The data is used to evaluate eight language models across sizes and architectures and explore mitigation through fine-tuning on community and progressive media content. Results show that language models reproduce anti-queer stereotypes, with variation across identities and models. Differences between the translated and community-based data highlight the importance of cultural adaptation for multilingual bias evaluation. Fine-tuning reduces bias on average, but not consistently across models and identities. Warning: This text contains examples of anti-queer hateful language and stereotypes.
LLMs are increasingly used for interpersonal advice and as tools for studying social behavior across languages and cultures. A common shortcut for eliciting language- or culture-related variation is to ask a model to answer as a native speaker. We test whether this native-speaker persona reproduces the outputs obtained when models instead generate advice in the target language and translate the response back into English. Using 600 interpersonal advice questions across 13 languages and eight LLMs, we compare native-language generation followed by translation (NL) with native-speaker persona prompting (NP), measuring linguistic style, behavioral scaffolding, and forced-choice action recommendations. We find that NP and NL are not interchangeable. Compared to NL, NP often increases lexical social cues, including affiliation and positive tone, while reducing qualities such as concreteness and social attunement; NP also provides less actionable scaffolding in open-ended advice. In forced-choice scenarios, NP changes which action the model selects, favoring confrontation over redirection, with effect sizes varying across languages, topics, and models. Our results show that cross-lingual elicitation strategy is a consequential methodological choice that can change both how advice is framed and which actions models recommend.
Assessing claim check-worthiness is an essential first step in automated fact-checking pipelines. This work is motivated by a real deployment challenge at an early-stage startup: running large language models (LLMs) over every incoming claim is cost- and latency-prohibitive, yet smaller models sacrifice accuracy. We propose NN-PPI, a pointwise extension of Prediction-Powered Inference (PPI) that calibrates model predictions at inference time as a lightweight post-hoc layer, without re-training the underlying model. NN-PPI achieves weighted F1 gains ranging from 12% to 33.80% depending on the size and performance of the baseline model, bringing SLMs on par with larger LLMs. Beyond few-shot SLMs, NN-PPI further improves a production-deployed fine-tuned model, demonstrating that residual calibration is complementary to supervised fine-tuning. By recovering LLM-level accuracy from models that are an order of magnitude cheaper to serve, it makes accurate check-worthiness detection substantially cheaper to operate at scale. Our code and data can be found at https://anonymous.4open.science/r/arr-claim-worthiness-F237.
Large Reasoning Models produce Long Chains-of-Thought (LCoTs) which involve breaking down the problem into smaller reasoning steps before reaching the conclusion. However, these steps often contain contradictions, unsupported inferences, or irrelevant steps, even when the final answer is correct. We propose Long Chain-of-Thought Graph Verifier (LCoT-GV), a graph-based framework that represents LCoTs as reasoning graphs. Each node in the graph represents a reasoning step and the edges encode semantic and logical relations. A Graph Attention Network is then trained to predict chain-of-thought correctness from the reasoning graph. We construct a new graph-oriented verification dataset from multiple reasoning benchmarks for question answering in various domains. The results show that our method is competitive with the most similar approaches.
Synthetic data is increasingly used to train large language models (LLMs), yet its security implications remain poorly understood. Prior work on subliminal learning suggests that models can inherit behavioral traits from seemingly unrelated training data. In this work, we investigate whether such mechanisms can be exploited to inject targeted social biases into aligned models through semantically benign synthetic data. We construct a pipeline in which a misaligned teacher model generates filtered synthetic datasets across domains such as creative writing and code generation, which are then used to fine-tune aligned student models. Our experiments show that benign-looking synthetic data can act as a covert channel for transmitting targeted biases while largely preserving the student model's general task capabilities. These results reveal a previously underexplored security risk in synthetic data-driven LLM training pipelines and highlight the need for improved safeguards. As one possible step toward this goal, we suggest that log-linearity-based scoring may provide a useful signal for screening seemingly benign synthetic data.
Minkyung Cho, Jihyo Kim, SeungWoo Song et al.· 0 citations
We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question answering and image-grounded hallucination detection in English and Modern Standard Arabic (MSA), and (ii) CRAI-Bench, evaluating the cultural accuracy of text-to-image generation. A total of 14 teams participated in the test phase, with 12 teams submitting system description papers. Participating systems used a range of approaches, including zero-shot prompting, fine-tuning of vision-language models, speech-recognition pipelines, ensembling, and score calibration. We describe the task setup, datasets, evaluation procedure, and participating systems, and summarize the main results across the different tracks. All datasets and evaluation scripts from the shared task are released to the research community. The shared task highlights the challenges of culturally grounded multimodal evaluation, particularly for Arabic speech and image-text reasoning.
Large language models exhibit substantial performance variation across languages, even when solving semantically equivalent tasks. Existing analyses often treat this phenomenon as an observational disparity caused by differences in pretraining data, tokenization, or benchmark coverage. We study a complementary hypothesis: high-resource languages (HRLs) may more reliably elicit latent computations useful for task-specific (i.e. mathematical) reasoning, while lower-resource languages (LRLs) may under-activate those computations despite expressing the same task. To test this hypothesis, we introduce a mechanistic intervention framework for identifying and transferring task-relevant sparse latent features across languages. Using sparse autoencoders over residual-stream activations, we isolate features enriched in successful HRL task-specific reasoning while filtering out source-language and generic-generation features. We then construct steering directions from these features and inject them during LRL inference. The resulting interventions test whether the selected features are functionally involved in the observed reasoning gap: suppressing them should impair source-language reasoning, while activating them should partially recover target-language reasoning beyond random and non-task controls. Our framework reframes some cross-lingual reasoning gaps as failures of mechanism elicitation rather than capability absence, and offers a causally testable route to feature-mediated transfer without translation, fine-tuning, or changing the user-facing language.
Minju Song, Hyeon Hwang, Junhyun Lee et al.· 0 citations
