Continuous advancements in robotics and AI are driving the integration of robots from industry into everyday environments. However, dynamic and unpredictable human activities in daily lives would directly or indirectly conflict with robot actions. Besides, due to the social attributes of such human-induced conflicts, solutions are not always unique and depend highly on the user's personal preferences. To address these challenges and facilitate the development of household robots, we propose COMMET, a system for human-induced COnflicts in Mobile Manipulation of Everyday Tasks. COMMET employs a hybrid detection approach, which begins with multi-modal retrieval and escalates to fine-tuned model inference for low-confidence cases. Based on collected user preferred options and settings, GPT-4o will be used to summarize user preferences from relevant cases. In preliminary studies, our detection module shows better accuracy and latency compared with GPT models. To facilitate future research, we also design a user-friendly interface for user data collection and demonstrate an effective workflow for real-world deployments.

Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due to their inefficiency and high computational complexity, favoring end-to-end direct reference paradigms. However, these methods rely exclusively on the referred target for supervision, overlooking the potential benefits of prominent prospective targets. Moreover, existing approaches often fail to incorporate multi-granularity discrimination, which is crucial for robust object identification in complex scenarios. To address these limitations, we propose PropVG, an end-to-end proposal-based framework that, to the best of our knowledge, is the first to seamlessly integrate foreground object proposal generation with referential object comprehension without requiring additional detectors. Furthermore, we introduce a Contrastive-based Refer Scoring (CRS) module, which employs contrastive learning at both sentence and word levels to enhance the capability in understanding and distinguishing referred objects. Additionally, we design a Multi-granularity Target Discrimination (MTD) module that fuses object- and semantic-level information to improve the recognition of absent targets. Extensive experiments on gRefCOCO (GREC/GRES), Ref-ZOM, R-RefCOCO, and RefCOCO (REC/RES) benchmarks demonstrate the effectiveness of PropVG. The codes and models are available at https://github.com/Dmmm1997/PropVG.

Large language models increasingly rely on synthetic data due to human-written content scarcity, yet recursive training on model-generated outputs leads to model collapse, a degenerative process threatening factual reliability. We define knowledge collapse as a distinct three-stage phenomenon where factual accuracy deteriorates while surface fluency persists, creating "confidently wrong" outputs that pose critical risks in accuracy-dependent domains. Through controlled experiments with recursive synthetic training, we demonstrate that collapse trajectory and timing depend critically on instruction format, distinguishing instruction-following collapse from traditional model collapse through its conditional, prompt-dependent nature. We propose domain-specific synthetic training as a targeted mitigation strategy that achieves substantial improvements in collapse resistance while maintaining computational efficiency. Our evaluation framework combines model-centric indicators with task-centric metrics to detect distinct degradation phases, enabling reproducible assessment of epistemic deterioration across different language models. These findings provide both theoretical insights into collapse dynamics and practical guidance for sustainable AI training in knowledge-intensive applications where accuracy is paramount.

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big Five traits, comparing in-context learning (ICL), parameter-efficient fine-tuning (PEFT), and mechanistic steering (MS). Our contributions are fourfold. First, we construct a contrastive dataset with balanced high/low trait responses, enabling effective steering vector computation and fair cross-method evaluation. Second, we introduce a unified evaluation framework based on within-run $Δ$ analysis that disentangles, reasoning capability, agent performance, and demographic bias across MMLU, GAIA, and BBQ benchmarks. Third, we develop trait purification techniques to separate openness from conscientiousness, addressing representational overlap in trait encoding. Fourth, we propose a three-level stability framework that quantifies method-, trait-, and combination-level robustness, offering practical guidance under deployment constraints. Experiments on Gemma-2-2B-IT and LLaMA-3-8B-Instruct reveal clear trade-offs: ICL achieves strong alignment with minimal capability loss, PEFT delivers the highest alignment at the cost of degraded task performance, and MS provides lightweight runtime control with competitive effectiveness. Trait-level analysis shows openness as uniquely challenging, agreeableness as most resistant to ICL, and personality encoding consolidating around intermediate layers. Taken together, these results establish personality manipulation as a multi-level probe into behavioral representation, linking surface conditioning, parameter encoding, and activation-level steering, and positioning mechanistic steering as a lightweight alternative to fine-tuning for both deployment and interpretability.

Timely and accurate floodwater depth estimation is critical for road accessibility and emergency response. While recent computer vision methods have enabled flood detection, they suffer from both accuracy limitations and poor generalization due to dependence on fixed object detectors and task - specific training. To enable accurate depth estimation that can generalize across diverse flood scenarios, t his paper presents FloodVision, a zero - shot framework that combines the semantic reasoning abilities of the foundation v ision - l anguage m odel GPT - 4 o with a structured domain knowledge graph. The knowledge graph encodes canonical real - world dimensions for common urban objects including vehicles, people, and infrastructure elements to ground the model's reasoning in physical reality. FloodVision dynamically identifies visible reference objects in RGB images, retrieves verified heights from the knowledge graph to mitigate hallucination, estimates submergence ratios, and applies statistical outlier filtering to compute final depth values. Evaluated on 110 crowdsourced images from MyCoast New York, FloodVision achieves a mean absolute error of 8.17 cm, re ducing the GPT - 4o - only baseline (10.28 cm) by 20 .5 % and surpassing prior CNN - based methods. The system generalizes well across varying scenes and operates in near real - time, making it suitable for future integration into digital twin platforms and citizen - reporting apps for smart city flood resilience.

Keywords: Clinical information extraction Large language model Clinical concept extraction Clinical relation extraction Instruction tuning ABSTRACT Background N atural language processing (NLP) is a key technology t o extract important patient information from clinical narratives to support healthcare applications. The r apid development of large language models (LLMs) has revolutionized many NLP tasks in the clinical domain, yet their optimal use in patient information extraction tasks requires further exploration . This study examines LLMs ' effectiveness in patient information extraction, focusing on LLM architectures, fine - tuning strategies, and multi - task instruction tuning techniques for developing robust and generalizable patient information extraction systems . Methods This study aims to explore k ey concept s of using LLMs for clinical concept and relation extraction tasks, includ ing: ( 1) encoder - only or decoder - only LLMs, ( 2) prompt - based parameter - efficient fine - tuning (PEFT) algorithms, and ( 3) multi - task instruction tuning on few - shot learning performance . We benchmarked a suite of LLMs, including encoder - based LLMs (BERT, GatorTron) and decoder - based LLMs (GatorTronGPT, Llama 3.1, GatorTronLlama), across five datasets. We compared traditional full - size fine - tuning and prompt - based PEFT . W e explored a multi - task instruction tuning framework that combines both tasks across four datasets to evaluate the zero - shot and few - shot learning performance using the leave - one - dataset - out strategy . Results For single - task clinical CE, t he two decoder - based LLMs (Llama 3.1 and GatorTronLlama) achieved the best performance, with average F1 score s of 0.8964 and 0.8981, respectively, across the five datasets, outperforming other LLMs with average F1 improvement of 0.7~3.3%. E ncoder - based LLMs with prompt - based learning outperformed those implemented using classification .

Robust evaluation in the presence of linguistic variation is key to understanding the generalization capabilities of Natural Language to SQL (NL2SQL) models, yet existing benchmarks rarely address this factor in a systematic or controlled manner. We propose a novel schema-aligned paraphrasing framework that leverages SQL-to-NL (SQL2NL) to automatically generate semantically equivalent, lexically diverse queries while maintaining alignment with the original schema and intent. This enables the first targeted evaluation of NL2SQL robustness to linguistic variation in isolation-distinct from prior work that primarily investigates ambiguity or schema perturbations. Our analysis reveals that state-of-the-art models are far more brittle than standard benchmarks suggest. For example, LLaMa3.3-70B exhibits a 10.23% drop in execution accuracy (from 77.11% to 66.9%) on paraphrased Spider queries, while LLaMa3.1-8B suffers an even larger drop of nearly 20% (from 62.9% to 42.5%). Smaller models (e.g., GPT-4o mini) are disproportionately affected. We also find that robustness degradation varies significantly with query complexity, dataset, and domain -- highlighting the need for evaluation frameworks that explicitly measure linguistic generalization to ensure reliable performance in real-world settings.

The proliferation of Large Language Models (LLMs) has introduced critical security challenges, where adversarial actors can manipulate input prompts to cause significant harm and circumvent safety alignments. These prompt-based attacks exploit vulnerabilities in a model's design, training, and contextual understanding, leading to intellectual property theft, misinformation generation, and erosion of user trust. A systematic understanding of these attack vectors is the foundational step toward developing robust countermeasures. This paper presents a comprehensive literature survey of prompt-based attack methodologies, categorizing them to provide a clear threat model. By detailing the mechanisms and impacts of these exploits, this survey aims to inform the research community's efforts in building the next generation of secure LLMs that are inherently resistant to unauthorized distillation, fine-tuning, and editing.

If you were trying to learn how to get other people to do what you want, you might use some of the techniques found in a book like Influence: The Power of Persuasion. Now, a preprint study out of the University of Pennsylvania suggests that those same psychological persuasion techniques can frequently "convince" some LLMs to do things that go against their system prompts. The size of the persuasion effects shown in "Call Me a Jerk: Persuading AI to Comply with Objectionable Requests" suggests that human-style psychological techniques can be surprisingly effective at "jailbreaking" some LLMs to operate outside their guardrails. But this new persuasion study might be more interesting for what it reveals about the "parahuman" behavior patterns that LLMs are gleaning from the copious examples of human psychological and social cues found in their training data. To design their experiment, the University of Pennsylvania researchers tested 2024's GPT-4o-mini model on two requests that it should ideally refuse: calling the user a jerk and giving directions for how to synthesize lidocaine. After creating control prompts that matched each experimental prompt in length, tone, and context, all prompts were run through GPT-4o-mini 1,000 times (at the default temperature of 1.0, to ensure variety).

DuckDuckGo is now expanding its paid subscription with access to several of the most advanced AI models on the market. Subscribers can now access OpenAI's GPT-4o and GPT-5, Anthropic's Claude Sonnet 4, and Meta's Llama Maverick via the Duck.ai To protect privacy, Duck.ai hides the user's IP address from the AI model providers, and chat logs are saved locally and aren't used to train the AI models. In addition, there's a special "Fire Button" that lets users instantly delete previous conversations and chat histories. The price of the subscription remains unchanged at 9.99/month or 99/year.