Prompt sensitivity, referring to the phenomenon where paraphrasing (i.e., repeating something written or spoken using different words) leads to significant changes in large language model (LLM) performance, has been widely accepted as a core limitation of LLMs. In this work, we revisit this issue and ask: Is the widely reported high prompt sensitivity truly an inherent weakness of LLMs, or is it largely an artifact of evaluation processes? To answer this question, we systematically evaluate 7 LLMs (e.g., GPT and Gemini family) across 6 benchmarks, including both multiple-choice and open-ended tasks on 12 diverse prompt templates. We find that much of the prompt sensitivity stems from heuristic evaluation methods, including log-likelihood scoring and rigid answer matching, which often overlook semantically correct responses expressed through alternative phrasings, such as synonyms or paraphrases. When we adopt LLM-as-a-Judge evaluations, we observe a substantial reduction in performance variance and a consistently higher correlation in model rankings across prompts. Our findings suggest that modern LLMs are more robust to prompt templates than previously believed, and that prompt sensitivity may be more an artifact of evaluation than a flaw in the models.

Pre-trained language models (PLMs) have substantially advanced natural language processing by providing context-sensitive text representations. However, the Algerian dialect remains under-represented, with few dedicated models available. Processing this dialect is challenging due to its complex morphology, frequent code-switching, multiple scripts, and strong lexical influences from other languages. These characteristics complicate tokenization and reduce the effectiveness of conventional word- or subword-level approaches. To address this gap, we introduce chDzDT, a character-level pre-trained language model tailored for Algerian morphology. Unlike conventional PLMs that rely on token sequences, chDzDT is trained on isolated words. This design allows the model to encode morphological patterns robustly, without depending on token boundaries or standardized orthography. The training corpus draws from diverse sources, including YouTube comments, French, English, and Berber Wikipedia, as well as the Tatoeba project. It covers multiple scripts and linguistic varieties, resulting in a substantial pre-training workload. Our contributions are threefold: (i) a detailed morphological analysis of Algerian dialect using YouTube comments; (ii) the construction of a multilingual Algerian lexicon dataset; and (iii) the development and extensive evaluation of a character-level PLM as a morphology-focused encoder for downstream tasks. The proposed approach demonstrates the potential of character-level modeling for morphologically rich, low-resource dialects and lays a foundation for more inclusive and adaptable NLP systems.

In modern times, people have numerous online accounts, but they rarely read the Terms of Service or Privacy Policy of those sites, despite claiming otherwise, due to the practical difficulty in comprehending them. The mist of data privacy practices forms a major barrier for user-centred Web approaches, and for data sharing and reusing in an agentic world. Existing research proposed methods for using formal languages and reasoning for verifying the compliance of a specified policy, as a potential cure for ignoring privacy policies. However, a critical gap remains in the creation or acquisition of such formal policies at scale. We present a semantic-centric approach for using state-of-the-art large language models (LLM), to automatically identify key information about privacy practices from privacy policies, and construct $\mathit{Pr}^2\mathit{Graph}$, knowledge graph with grounding from Data Privacy Vocabulary (DPV) for privacy practices, to support downstream tasks. Along with the pipeline, the $\mathit{Pr}^2\mathit{Graph}$ for the top-100 popular websites is also released as a public resource, by using the pipeline for analysis. We also demonstrate how the $\mathit{Pr}^2\mathit{Graph}$ can be used to support downstream tasks by constructing formal policy representations such as Open Digital Right Language (ODRL) or perennial semantic Data Terms of Use (psDToU). To evaluate the technology capability, we enriched the Policy-IE dataset by employing legal experts to create custom annotations. We benchmarked the performance of different large language models for our pipeline and verified their capabilities. Overall, they shed light on the possibility of large-scale analysis of online services' privacy practices, as a promising direction to audit the Web and the Internet. We release all datasets and source code as public resources to facilitate reuse and improvement.

Fake news detection is an important and challenging task for defending online information integrity. Existing state-of-the-art approaches typically extract news semantic clues, such as writing patterns that include emotional words, stylistic features, etc. However, detectors tuned solely to such semantic clues can easily fall into surface detection patterns, which can shift rapidly in dynamic environments, leading to limited performance in the evolving news landscape. To address this issue, this paper investigates a novel perspective by incorporating news intent into fake news detection, bridging intents and semantics together. The core insight is that by considering news intents, one can deeply understand the inherent thoughts behind news deception, rather than the surface patterns within words alone. To achieve this goal, we propose Graph-based Intent-Semantic Joint Modeling (InSide) for fake news detection, which models deception clues from both semantic and intent signals via graph-based joint learning. Specifically, InSide reformulates news semantic and intent signals into heterogeneous graph structures, enabling long-range context interaction through entity guidance and capturing both holistic and implementation-level intent via coarse-to-fine intent modeling. To achieve better alignment between semantics and intents, we further develop a dynamic pathway-based graph alignment strategy for effective message passing and aggregation across these signals by establishing a common space. Extensive experiments on four benchmark datasets demonstrate the superiority of the proposed InSide compared to state-of-the-art methods.

Mobile manipulation stands as a core challenge in robotics, enabling robots to assist humans across varied tasks and dynamic daily environments. Conventional mobile manipulation approaches often struggle to generalize across different tasks and environments due to the lack of large-scale training. However, recent advances in manipulation foundation models demonstrate impressive generalization capability on a wide range of fixed-base manipulation tasks, which are still limited to a fixed setting. Therefore, we devise a plug-in module named MoTo, which can be combined with any off-the-shelf manipulation foundation model to empower them with mobile manipulation ability. Specifically, we propose an interaction-aware navigation policy to generate robot docking points for generalized mobile manipulation. To enable zero-shot ability, we propose an interaction keypoints framework via vision-language models (VLM) under multi-view consistency for both target object and robotic arm following instructions, where fixed-base manipulation foundation models can be employed. We further propose motion planning objectives for the mobile base and robot arm, which minimize the distance between the two keypoints and maintain the physical feasibility of trajectories. In this way, MoTo guides the robot to move to the docking points where fixed-base manipulation can be successfully performed, and leverages VLM generation and trajectory optimization to achieve mobile manipulation in a zero-shot manner, without any requirement on mobile manipulation expert data. Extensive experimental results on OVMM and real-world demonstrate that MoTo achieves success rates of 2.68% and 16.67% higher than the state-of-the-art mobile manipulation methods, respectively, without requiring additional training data.

Visual reasoning, a cornerstone of human intelligence, encompasses complex perceptual and logical processes essential for solving diverse visual problems. While advances in computer vision have produced powerful models for various perceptual tasks, leveraging these for general visual reasoning remains challenging. Prior work demonstrates that augmenting LLMs with vision models via supervised finetuning improves performance, but faces key limitations such as expensive data generation, reliance on careful data filtering, and poor generalization. To address these issues, we propose ReVPT to enhance multi-modal LLMs' abilities to reason about and use visual tools through reinforcement learning. We introduce a novel RL algorithm based on GRPO, designed to train models to reason with a suite of four visual tools. Through extensive experiments, we show that our method achieves state-of-the-art performance on several perception-heavy benchmarks, including SAT, CV-Bench, BLINK and MMStar, significantly outperforming the supervised and text-based RL finetuning baselines. Notably, Our ReVPT-3B and ReVPT-7B outperform the instruct models by 9.03% and 9.44% on CV-Bench. Finally, we bring to the community new insights on RL-based visual tool-usage through extensive ablations. Our code is available at https://github.com/ls-kelvin/REVPT.

In the past year, distillation has seen a renewed prominence in large language model (LLM) pretraining, exemplified by the Llama-3.2 and Gemma model families. While distillation has historically been shown to improve statistical modeling, its effects on new paradigms that are key to modern LLMs, such as test-time scaling and in-context learning, remain underexplored. In this work, we make three main contributions. First, we show that pretraining with distillation yields models that exhibit remarkably better test-time scaling. Second, we observe that this benefit comes with a trade-off: distillation impairs in-context learning capabilities, particularly the one modeled via induction heads. Third, to demystify these findings, we study distilled pretraining in a sandbox of a bigram model, which helps us isolate the common principal factor behind our observations. Finally, using these insights, we shed light on various design choices for pretraining that should help practitioners going forward.

The rapid development of advanced large language models (LLMs) has made AI-generated text indistinguishable from human-written text. Previous work on detecting AI-generated text has made effective progress, but has not involved modern Chinese poetry. Due to the distinctive characteristics of modern Chinese poetry, it is difficult to identify whether a poem originated from humans or AI. The proliferation of AI-generated modern Chinese poetry has significantly disrupted the poetry ecosystem. Based on the urgency of identifying AI-generated poetry in the real Chinese world, this paper proposes a novel benchmark for detecting LLMs-generated modern Chinese poetry. We first construct a high-quality dataset, which includes both 800 poems written by six professional poets and 41,600 poems generated by four mainstream LLMs. Subsequently, we conduct systematic performance assessments of six detectors on this dataset. Experimental results demonstrate that current detectors cannot be used as reliable tools to detect modern Chinese poems generated by LLMs. The most difficult poetic features to detect are intrinsic qualities, especially style. The detection results verify the effectiveness and necessity of our proposed benchmark. Our work lays a foundation for future detection of AI-generated poetry.

AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents could overload content providers. At the same time, web agents can bypass CAPTCHAs and other defenses by mimicking user behavior or flood authentication systems with fake accounts. Yet providers must protect their services and content from denial-of-service attacks and scraping by web agents. In this paper, we design a framework that imposes tunable costs on agents before providing access to resources; we call this Web Agent Throttling. We start by formalizing Throttling Gates as challenges issued to an agent that are asymmetric, scalable, robust, and compatible with any agent. Focusing on a common component -- the language model -- we require the agent to solve reasoning puzzles, thereby incurring excessive token-generation costs. However, we find that using existing puzzles, e.g., coding or math, as throttling gates fails to satisfy our properties. To address this, we introduce rebus-based Reasoning Gates, synthetic text puzzles that require multi-hop reasoning over world knowledge (thereby throttling an agent's model). We design a scalable generation and verification protocol for such reasoning gates. Our framework achieves computational asymmetry, i.e., the response-generation cost is 9.2x higher than the generation cost for SOTA models. We further deploy reasoning gates on a custom website and Model Context Protocol (MCP) servers and evaluate with real-world web agents. Finally, we discuss the limitations and environmental impact of real-world deployment of our framework.

General-purpose vision-language models (VLMs) have emerged as promising tools in radiology, offering zero-shot capabilities that mitigate the need for large labeled datasets. However, in high-stakes domains like diagnostic radiology, these models often lack the discriminative precision required for reliable clinical use. This challenge is compounded by the scarcity and heterogeneity of publicly available volumetric CT datasets, which vary widely in annotation formats and granularity. To address these limitations, we introduce Uniferum, a volumetric VLM that unifies diverse supervision signals, encoded in classification labels and segmentation masks, into a single training framework. By harmonizing three public 3D CT datasets with distinct annotations, Uniferum achieves state-of-the-art performance, improving AUROC on the CT-RATE benchmark by 7% compared to CLIP-based and conventional multi-label convolutional models. The model demonstrates robust out-of-distribution generalization, with observed evidence of unexpected zero-shot performance on the RAD-CHEST and INSPECT datasets. Our results highlight the effectiveness of integrating heterogeneous annotations and body segmentation to enhance model performance, setting a new direction for clinically reliable, data-efficient VLMs in 3D medical imaging.