The assessment of legal problems requires the consideration of a specific legal system and its levels of abstraction, from constitutional law to statutory law to case law. The extent to which Large Language Models (LLMs) internalize such legal systems is unknown. In this paper, we propose and investigate different approaches to condition LLMs at different levels of abstraction in legal systems. This paper examines different approaches to conditioning LLMs at multiple levels of abstraction in legal systems to detect potentially punishable hate speech. We focus on the task of classifying whether a specific social media posts falls under the criminal offense of incitement to hatred as prescribed by the German Criminal Code. The results show that there is still a significant performance gap between models and legal experts in the legal assessment of hate speech, regardless of the level of abstraction with which the models were conditioned. Our analysis revealed, that models conditioned on abstract legal knowledge lacked deep task understanding, often contradicting themselves and hallucinating answers, while models using concrete legal knowledge performed reasonably well in identifying relevant target groups, but struggled with classifying target conducts.

Privacy policies inform users about data collection and usage, yet their complexity limits accessibility for diverse populations. Existing Privacy Policy Question Answering (QA) systems exhibit performance disparities across English dialects, disadvantaging speakers of non-standard varieties. We propose a novel multi-agent framework inspired by human-centered design principles to mitigate dialectal biases. Our approach integrates a Dialect Agent, which translates queries into Standard American English (SAE) while preserving dialectal intent, and a Privacy Policy Agent, which refines predictions using domain expertise. Unlike prior approaches, our method does not require retraining or dialect-specific fine-tuning, making it broadly applicable across models and domains. Evaluated on PrivacyQA and PolicyQA, our framework improves GPT-4o-mini's zero-shot accuracy from 0.394 to 0.601 on PrivacyQA and from 0.352 to 0.464 on PolicyQA, surpassing or matching few-shot baselines without additional training data. These results highlight the effectiveness of structured agent collaboration in mitigating dialect biases and underscore the importance of designing NLP systems that account for linguistic diversity to ensure equitable access to privacy information.

Large language models (LLMs) have demonstrated emergent abilities across diverse tasks, raising the question of whether they acquire internal world models. In this work, we investigate whether LLMs implicitly encode linear spatial world models, which we define as linear representations of physical space and object configurations. We introduce a formal framework for spatial world models and assess whether such structure emerges in contextual embeddings. Using a synthetic dataset of object positions, we train probes to decode object positions and evaluate geometric consistency of the underlying space. We further conduct causal interventions to test whether these spatial representations are functionally used by the model. Our results provide empirical evidence that LLMs encode linear spatial world models.

Idioms are defined as a group of words with a figurative meaning not deducible from their individual components. Although modern machine translation systems have made remarkable progress, translating idioms remains a major challenge, especially for speech-to-text systems, where research on this topic is notably sparse. In this paper, we systematically evaluate idiom translation as compared to conventional news translation in both text-to-text machine translation (MT) and speech-to-text translation (SLT) systems across two language pairs (German to English, Russian to English). We compare state-of-the-art end-to-end SLT systems (SeamlessM4T SLT-to-text, Whisper Large v3) with MT systems (SeamlessM4T SLT-to-text, No Language Left Behind), Large Language Models (DeepSeek, LLaMA) and cascaded alternatives. Our results reveal that SLT systems experience a pronounced performance drop on idiomatic data, often reverting to literal translations even in higher layers, whereas MT systems and Large Language Models demonstrate better handling of idioms. These findings underscore the need for idiom-specific strategies and improved internal representations in SLT architectures.

Background: Large language models (LLMs) have demonstrated substantial potential to support clinical practice. Other than Chat GPT4 and its predecessors, few LLMs, especially those of the leading and more powerful reasoning model class, have been subjected to medical specialty examination questions, including in the domain of primary care. This paper aimed to test the capabilities of leading LLMs as of May 2025 (o3, Claude Opus 4, Grok3, and Gemini 2.5 Pro) in primary care education, specifically in answering Member of the Royal College of General Practitioners (MRCGP) style examination questions. Methods: o3, Claude Opus 4, Grok3, and Gemini 2.5 Pro were tasked to answer 100 randomly chosen multiple choice questions from the Royal College of General Practitioners GP SelfTest on 25 May 2025. Questions included textual information, laboratory results, and clinical images. Each model was prompted to answer as a GP in the UK and was provided with full question information. Each question was attempted once by each model. Responses were scored against correct answers provided by GP SelfTest. Results: The total score of o3, Claude Opus 4, Grok3, and Gemini 2.5 Pro was 99.0%, 95.0%, 95.0%, and 95.0%, respectively. The average peer score for the same questions was 73.0%. Discussion: All models performed remarkably well, and all substantially exceeded the average performance of GPs and GP registrars who had answered the same questions. o3 demonstrated the best performance, while the performances of the other leading models were comparable with each other and were not substantially lower than that of o3. These findings strengthen the case for LLMs, particularly reasoning models, to support the delivery of primary care, especially those that have been specifically trained on primary care clinical data.

With the advancement of language models, unified multimodal understanding and generation have made significant strides, with model architectures evolving from separated components to unified single-model frameworks. This paper explores an efficient training paradigm to build a single transformer for unified multimodal understanding and generation. Specifically, we propose a multimodal warmup strategy utilizing prior knowledge to extend capabilities. To address cross-modal compatibility challenges, we introduce feature pre-scaling and multimodal AdaLN techniques. Integrating the proposed technologies, we present the HaploOmni, a new single multimodal transformer. With limited training costs, HaploOmni achieves competitive performance across multiple image and video understanding and generation benchmarks over advanced unified models. All codes will be made public at https://github.com/Tencent/HaploVLM.

The misuse of large language models (LLMs) poses potential risks, motivating the development of machine-generated text (MGT) detection. Existing literature primarily concentrates on binary, document-level detection, thereby neglecting texts that are composed jointly by human and LLM contributions. Hence, this paper explores the possibility of fine-grained MGT detection under human-AI coauthoring. We suggest fine-grained detectors can pave pathways toward coauthored text detection with a numeric AI ratio. Specifically, we propose a dataset, HACo-Det, which produces human-AI coauthored texts via an automatic pipeline with word-level attribution labels. We retrofit seven prevailing document-level detectors to generalize them to word-level detection. Then we evaluate these detectors on HACo-Det on both word- and sentence-level detection tasks. Empirical results show that metric-based methods struggle to conduct fine-grained detection with a 0.462 average F1 score, while finetuned models show superior performance and better generalization across domains. However, we argue that fine-grained co-authored text detection is far from solved. We further analyze factors influencing performance, e.g., context window, and highlight the limitations of current methods, pointing to potential avenues for improvement.

Counterfactual inference is a powerful tool for analysing and evaluating autonomous agents, but its application to language model (LM) agents remains challenging. Existing work on counterfactuals in LMs has primarily focused on token-level counterfactuals, which are often inadequate for LM agents due to their open-ended action spaces. Unlike traditional agents with fixed, clearly defined action spaces, the actions of LM agents are often implicit in the strings they output, making their action spaces difficult to define and interpret. Furthermore, the meanings of individual tokens can shift depending on the context, adding complexity to token-level reasoning and sometimes leading to biased or meaningless counterfactuals. We introduce \emph{Abstract Counterfactuals}, a framework that emphasises high-level characteristics of actions and interactions within an environment, enabling counterfactual reasoning tailored to user-relevant features. Our experiments demonstrate that the approach produces consistent and meaningful counterfactuals while minimising the undesired side effects of token-level methods. We conduct experiments on text-based games and counterfactual text generation, while considering both token-level and latent-space interventions.

We propose a training-free, Vision-Language Model (VLM)-guided approach for efficiently generating trajectories to facilitate target inspection planning based on text descriptions. Unlike existing Vision-and-Language Navigation (VLN) methods designed for general agents in unknown environments, our approach specifically targets the efficient inspection of known scenes, with widespread applications in fields such as medical, marine, and civil engineering. Leveraging VLMs, our method first extracts points of interest (POIs) from the text description, then identifies a set of waypoints from which POIs are both salient and align with the spatial constraints defined in the prompt. Next, we interact with the VLM to iteratively refine the trajectory, preserving the visibility and prominence of the POIs. Further, we solve a Traveling Salesman Problem (TSP) to find the most efficient visitation order that satisfies the order constraint implied in the text description. Finally, we apply trajectory optimization to generate smooth, executable inspection paths for aerial and underwater vehicles. We have evaluated our method across a series of both handcrafted and real-world scanned environments. The results demonstrate that our approach effectively generates inspection planning trajectories that adhere to user instructions.

Cell type annotation is a key task in analyzing the heterogeneity of single-cell RNA sequencing data. Although recent foundation models automate this process, they typically annotate cells independently, without considering batch-level cellular context or providing explanatory reasoning. In contrast, human experts often annotate distinct cell types for different cell clusters based on their domain knowledge. To mimic this workflow, we introduce the CellPuzzles task, where the objective is to assign unique cell types to a batch of cells. This benchmark spans diverse tissues, diseases, and donor conditions, and requires reasoning across the batch-level cellular context to ensure label uniqueness. We find that off-the-shelf large language models (LLMs) struggle on CellPuzzles, with the best baseline (OpenAI's o1) achieving only 19.0% batch-level accuracy. To fill this gap, we propose Cell-o1, a 7B LLM trained via supervised fine-tuning on distilled reasoning traces, followed by reinforcement learning with batch-level rewards. Cell-o1 achieves state-of-the-art performance, outperforming o1 by over 73% and generalizing well across contexts. Further analysis of training dynamics and reasoning behaviors provides insights into batch-level annotation performance and emergent expert-like reasoning. Code and data are available at https://github.com/ncbi-nlp/cell-o1.