Large Language Models (LLMs) demonstrate impressive reasoning capabilities in familiar contexts, but struggle when the context conflicts with their parametric knowledge. To investigate this phenomenon, we introduce CounterLogic, a dataset containing 1,800 examples across 9 logical schemas, explicitly designed to evaluate logical reasoning through counterfactual (hypothetical knowledge-conflicting) scenarios. Our systematic evaluation of 11 LLMs across 6 different datasets reveals a consistent performance degradation, with accuracies dropping by 27% on average when reasoning through counterfactual information. We propose Self-Segregate, a prompting method enabling metacognitive awareness (explicitly identifying knowledge conflicts) before reasoning. Our method dramatically narrows the average performance gaps from 27% to just 11%, while significantly increasing the overall accuracy (+7.5%). We discuss the implications of these findings and draw parallels to human cognitive processes, particularly on how humans disambiguate conflicting information during reasoning tasks. Our findings offer practical insights for understanding and enhancing LLMs reasoning capabilities in real-world applications, especially where models must logically reason independently of their factual knowledge.

With the advent of 6G communications, intelligent communication systems face multiple challenges, including constrained perception and response capabilities, limited scalability, and low adaptability in dynamic environments. This tutorial provides a systematic introduction to the principles, design, and applications of Large Artificial Intelligence Models (LAMs) and Agentic AI technologies in intelligent communication systems, aiming to offer researchers a comprehensive overview of cutting-edge technologies and practical guidance. First, we outline the background of 6G communications, review the technological evolution from LAMs to Agentic AI, and clarify the tutorial's motivation and main contributions. Subsequently, we present a comprehensive review of the key components required for constructing LAMs. We further categorize LAMs and analyze their applicability, covering Large Language Models (LLMs), Large Vision Models (LVMs), Large Multimodal Models (LMMs), Large Reasoning Models (LRMs), and lightweight LAMs. Next, we propose a LAM-centric design paradigm tailored for communications, encompassing dataset construction and both internal and external learning approaches. Building upon this, we develop an LAM-based Agentic AI system for intelligent communications, clarifying its core components such as planners, knowledge bases, tools, and memory modules, as well as its interaction mechanisms. We also introduce a multi-agent framework with data retrieval, collaborative planning, and reflective evaluation for 6G. Subsequently, we provide a detailed overview of the applications of LAMs and Agentic AI in communication scenarios. Finally, we summarize the research challenges and future directions in current studies, aiming to support the development of efficient, secure, and sustainable next-generation intelligent communication systems.

Pretraining on large, semantically rich datasets is key for developing language models. Surprisingly, recent studies have shown that even synthetic data, generated procedurally through simple semantic-free algorithms, can yield some of the same benefits as natural language pretraining. It is unclear what specific capabilities such simple synthetic data instils in a model, where these capabilities reside in the architecture, and how they manifest within its weights. In this short paper, we identify several beneficial forms of procedural data, together with specific algorithmic reasoning skills that improve in small transformers. Our core finding is that different procedural rules instil distinct but complementary inductive structures in the model. With extensive ablations and partial-transfer experiments, we discover that these structures reside in different parts of the model. Attention layers often carry the most transferable information, but some pretraining rules impart useful structure to MLP blocks instead. Most interestingly, the structures induced by multiple rules can be composed to jointly reinforce multiple capabilities. These results suggest an exciting possibility of disentangling the acquisition of knowledge from reasoning in language models, with the goal of improving their robustness and data efficiency.

Large language models (LLMs) exhibit impressive language capabilities but remain vulnerable to malicious prompts and jailbreaking attacks. Existing knowledge editing methods for LLM detoxification face two major challenges. First, they often rely on entity-specific localization, making them ineffective against adversarial inputs without explicit entities. Second, these methods suffer from over-editing, where detoxified models reject legitimate queries, compromising overall performance. In this paper, we propose ToxEdit, a toxicity-aware knowledge editing approach that dynamically detects toxic activation patterns during forward propagation. It then routes computations through adaptive inter-layer pathways to mitigate toxicity effectively. This design ensures precise toxicity mitigation while preserving LLMs' general capabilities. To more accurately assess over-editing, we also enhance the SafeEdit benchmark by incorporating instruction-following evaluation tasks. Experimental results on multiple LLMs demonstrate that our ToxEdit outperforms previous state-of-the-art methods in both detoxification performance and safeguarding general capabilities of LLMs.

Large Language Models (LLMs) have demonstrated strong capabilities in multilingual machine translation, sometimes even outperforming traditional neural systems. However, previous research has highlighted the challenges of using LLMs, particularly with prompt engineering, for low-resource languages. In this work, we introduce Fragment-Shot Prompting, a novel in-context learning method that segments input and retrieves translation examples based on syntactic coverage, along with Pivoted Fragment-Shot, an extension that enables translation without direct parallel data. We evaluate these methods using GPT-3.5, GPT-4o, o1-mini, LLaMA-3.3, and DeepSeek-R1 for translation between Italian and two Ladin variants, revealing three key findings: (1) Fragment-Shot Prompting is effective for translating into and between the studied low-resource languages, with syntactic coverage positively correlating with translation quality; (2) Models with stronger reasoning abilities make more effective use of retrieved knowledge, generally produce better translations, and enable Pivoted Fragment-Shot to significantly improve translation quality between the Ladin variants; and (3) prompt engineering offers limited, if any, improvements when translating from a low-resource to a high-resource language, where zero-shot prompting already yields satisfactory results. We publicly release our code and the retrieval corpora.

Recent research has highlighted that Large Language Models (LLMs), even when trained to generate extended long reasoning steps, still face significant challenges on hard reasoning problems. However, much of the existing literature relies on direct prompting with simple in-context learning examples for evaluation, which largely overlooks advanced techniques to elicit LLMs' deliberate reasoning before drawing conclusions that LLMs hit a performance ceiling. In this paper, we systematically explore the combined potential of in-context search and test-time scaling on super hard reasoning tasks. We find that by employing advanced in-context search prompting to LLMs augmented with internal scaling, one can achieve transformative performance breakthroughs on tasks previously deemed "unsolvable" (e.g., reported success rates below 5%). We provide both empirical results and theoretical analysis of how this combination can unleash LLM reasoning capabilities: i) Empirically, on controlled NP-hard tasks and complex real-world planning benchmarks, our approach achieves up to a 30x improvement in success rates compared to previously reported results without any external mechanisms; ii) Theoretically, we show that in-context search prompting, when combined with internal scaling, significantly extends the complexity class of solvable reasoning problems. These findings challenge prevailing assumptions about the limitations of LLMs on complex tasks, indicating that current evaluation paradigms systematically underestimate their true potential. Our work calls for a critical reassessment of how LLM reasoning is benchmarked and a more robust evaluation strategy that fully captures the true capabilities of contemporary LLMs, which can lead to a better understanding of their operational reasoning boundaries in real-world deployments.

Foundation models have had a transformative impact on AI. A combination of large investments in research and development, growing sources of digital data for training, and architectures that scale with data and compute has led to models with powerful capabilities. Releasing assets is fundamental to scientific advancement and commercial enterprise. However, concerns over negligent or malicious uses of AI have led to the design of mechanisms to limit the risks of the technology. The result has been a proliferation of licenses with behavioral-use clauses and acceptable-use-policies that are increasingly being adopted by commonly used families of models (Llama, Gemma, Deepseek) and a myriad of smaller projects. We created and deployed a custom AI licenses generator to facilitate license creation and have quantitatively and qualitatively analyzed over 300 customized licenses created with this tool. Alongside this we analyzed 1.7 million models licenses on the HuggingFace model hub. Our results show increasing adoption of these licenses, interest in tools that support their creation and a convergence on common clause configurations. In this paper we take the position that tools for tracking adoption of, and adherence to, these licenses is the natural next step and urgently needed in order to ensure they have the desired impact of ensuring responsible use.

Evidence-based medicine (EBM) is at the forefront of modern healthcare, emphasizing the use of the best available scientific evidence to guide clinical decisions. Due to the sheer volume and rapid growth of medical literature and the high cost of curation, there is a critical need to investigate Natural Language Processing (NLP) methods to identify, appraise, synthesize, summarize, and disseminate evidence in EBM. This survey presents an in-depth review of 129 research studies on leveraging NLP for EBM, illustrating its pivotal role in enhancing clinical decision-making processes. The paper systematically explores how NLP supports the five fundamental steps of EBM -- Ask, Acquire, Appraise, Apply, and Assess. The review not only identifies current limitations within the field but also proposes directions for future research, emphasizing the potential for NLP to revolutionize EBM by refining evidence extraction, evidence synthesis, appraisal, summarization, enhancing data comprehensibility, and facilitating a more efficient clinical workflow.

While (multimodal) large language models (LLMs) have attracted widespread attention due to their exceptional capabilities, they remain vulnerable to jailbreak attacks. Various defense methods are proposed to defend against jailbreak attacks, however, they are often tailored to specific types of jailbreak attacks, limiting their effectiveness against diverse adversarial strategies. For instance, rephrasing-based defenses are effective against text adversarial jailbreaks but fail to counteract image-based attacks. To overcome these limitations, we propose a universal defense framework, termed Test-time IMmunization (TIM), which can adaptively defend against various jailbreak attacks in a self-evolving way. Specifically, TIM initially trains a gist token for efficient detection, which it subsequently applies to detect jailbreak activities during inference. When jailbreak attempts are identified, TIM implements safety fine-tuning using the detected jailbreak instructions paired with refusal answers. Furthermore, to mitigate potential performance degradation in the detector caused by parameter updates during safety fine-tuning, we decouple the fine-tuning process from the detection module. Extensive experiments on both LLMs and multimodal LLMs demonstrate the efficacy of TIM.

In this paper we expose our approach to solve the \textit{SemEval 2025 Task 8: Question-Answering over Tabular Data} challenge. Our strategy leverages Python code generation with LLMs to interact with the table and get the answer to the questions. The process is composed of multiple steps: understanding the content of the table, generating natural language instructions in the form of steps to follow in order to get the answer, translating these instructions to code, running it and handling potential errors or exceptions. These steps use open source LLMs and fine grained optimized prompts for each task (step). With this approach, we achieved a score of $70.50\%$ for subtask 1.