Uncategorized

arXiv:2512.14306v1 Announce Type: new Abstract: This paper investigates the ability of Large Language Models (LLMs), specifically GPT-3.5-turbo (GPT), to form inflation perceptions and expectations based on macroeconomic price signals. We compare the LLM’s output to household survey data and official statistics, mimicking the information set and demographic characteristics of the Bank of England’s Inflation Attitudes Survey (IAS). Our quasi-experimental design exploits the timing of GPT’s training cut-off in September 2021 which means it has no knowledge of the subsequent UK inflation surge. We find that GPT tracks aggregate survey projections and official statistics at short horizons. At a disaggregated level, GPT replicates key empirical regularities of households’ inflation perceptions, particularly for income, housing tenure, and social class. A novel Shapley value decomposition of LLM outputs suited for the synthetic survey setting provides well-defined insights into the drivers of model outputs linked to prompt content. We find that GPT demonstrates a heightened sensitivity to food inflation information similar to that of human respondents. However, we also find that it lacks a consistent model of consumer price inflation. More generally, our approach could be used to evaluate the behaviour of LLMs for use in the social sciences, to compare different models, or to assist in survey design.

arXiv:2511.22333v2 Announce Type: replace-cross Abstract: LLM serving is increasingly dominated by decode attention, which is a memory-bound operation due to massive KV cache loading from global memory. Meanwhile, real-world workloads exhibit substantial, hierarchical shared prefixes across requests (e.g., system prompts, tools/templates, RAG). Existing attention implementations fail to fully exploit prefix sharing: one-query-per-CTA execution repeatedly loads shared prefix KV cache, while one-size-fits-all tiling leaves on-chip resources idle and exacerbates bubbles for uneven KV lengths. These choices amplify memory bandwidth pressure and stall memory-bound decode attention. This paper introduces PAT, a prefix-aware attention kernel implementation for LLM decoding that organizes execution with a pack-forward-merge paradigm. PAT packs queries by shared prefix to reduce repeated memory accesses, runs a customized multi-tile kernel to achieve high resource efficiency. It further applies practical multi-stream forwarding and KV splitting to reduce resource bubbles. The final merge performs online softmax with negligible overhead. We implement PAT as an off-the-shelf plugin for vLLM. Evaluation on both real-world and synthetic workloads shows that PAT reduces attention latency by 53.5% on average and TPOT by 17.0-93.1% under the same configurations against state-of-the-art attention kernels. PAT’s source code is publicly available at https://github.com/flashserve/PAT.

arXiv:2510.17904v2 Announce Type: replace-cross Abstract: The proficiency of Large Language Models (LLMs) in processing structured data and adhering to syntactic rules is a capability that drives their widespread adoption but also makes them paradoxically vulnerable. In this paper, we investigate this vulnerability through BreakFun, a jailbreak methodology that weaponizes an LLM’s adherence to structured schemas. BreakFun employs a three-part prompt that combines an innocent framing and a Chain-of-Thought distraction with a core “Trojan Schema”–a carefully crafted data structure that compels the model to generate harmful content, exploiting the LLM’s strong tendency to follow structures and schemas. We demonstrate this vulnerability is highly transferable, achieving an average success rate of 89% across 13 foundational and proprietary models on JailbreakBench, and reaching a 100% Attack Success Rate (ASR) on several prominent models. A rigorous ablation study confirms this Trojan Schema is the attack’s primary causal factor. To counter this, we introduce the Adversarial Prompt Deconstruction guardrail, a defense that utilizes a secondary LLM to perform a “Literal Transcription”–extracting all human-readable text to isolate and reveal the user’s true harmful intent. Our proof-of-concept guardrail demonstrates high efficacy against the attack, validating that targeting the deceptive schema is a viable mitigation strategy. Our work provides a look into how an LLM’s core strengths can be turned into critical weaknesses, offering a fresh perspective for building more robustly aligned models.

arXiv:2509.21320v3 Announce Type: replace Abstract: We present a scientific reasoning foundation model that aligns natural language with heterogeneous scientific representations. The model is pretrained on a 206B-token corpus spanning scientific text, pure sequences, and sequence-text pairs, then aligned via SFT on 40M instructions, annealed cold-start bootstrapping to elicit long-form chain-of-thought, and reinforcement learning with task-specific reward shaping, which instills deliberate scientific reasoning. It supports four capability families, covering up to 103 tasks across workflows: (i) faithful translation between text and scientific formats, (ii) text/knowledge extraction, (iii) property prediction, (iv) property classification, (v) unconditional and conditional sequence generation and design. Compared with specialist systems, our approach broadens instruction coverage, improves cross-domain generalization, and enhances fidelity. We detail data curation and training and show that cross-discipline learning strengthens transfer and downstream reliability. The model, instruct tuning datasets and the evaluation code are open-sourced at https://huggingface.co/SciReason and https://github.com/open-sciencelab/SciReason.

arXiv:2512.13154v1 Announce Type: cross Abstract: Conversational agents often encounter ambiguous user requests, requiring an effective clarification to successfully complete tasks. While recent advancements in real-world applications favor multi-agent architectures to manage complex conversational scenarios efficiently, ambiguity resolution remains a critical and underexplored challenge–particularly due to the difficulty of determining which agent should initiate a clarification and how agents should coordinate their actions when faced with uncertain or incomplete user input. The fundamental questions of when to interrupt a user and how to formulate the optimal clarification query within the most optimal multi-agent settings remain open. In this paper, we propose MAC (Multi-Agent Clarification), an interactive multi-agent framework specifically optimized to resolve user ambiguities by strategically managing clarification dialogues. We first introduce a novel taxonomy categorizing user ambiguities to systematically guide clarification strategies. Then, we present MAC that autonomously coordinates multiple agents to interact synergistically with users. Empirical evaluations on MultiWOZ 2.4 demonstrate that enabling clarification at both levels increases task success rate 7.8% (54.5 to 62.3) and reduces the average number of dialogue turns (6.53 to 4.86) by eliciting all required user information up front and minimizing repetition. Our findings highlight the importance of active user interaction and role-aware clarification for more reliable human-agent communication.

arXiv:2512.12885v1 Announce Type: cross Abstract: Automated road sign recognition is a critical task for intelligent transportation systems, but traditional deep learning methods struggle with the sheer number of sign classes and the impracticality of creating exhaustive labeled datasets. This paper introduces a novel zero-shot recognition framework that adapts the Retrieval-Augmented Generation (RAG) paradigm to address this challenge. Our method first uses a Vision Language Model (VLM) to generate a textual description of a sign from an input image. This description is used to retrieve a small set of the most relevant sign candidates from a vector database of reference designs. Subsequently, a Large Language Model (LLM) reasons over the retrieved candidates to make a final, fine-grained recognition. We validate this approach on a comprehensive set of 303 regulatory signs from the Ohio MUTCD. Experimental results demonstrate the framework’s effectiveness, achieving 95.58% accuracy on ideal reference images and 82.45% on challenging real-world road data. This work demonstrates the viability of RAG-based architectures for creating scalable and accurate systems for road sign recognition without task-specific training.

arXiv:2512.12868v1 Announce Type: new Abstract: Large language models (LLMs) excel on multiple-choice clinical diagnosis benchmarks, yet it is unclear how much of this performance reflects underlying probabilistic reasoning. We study this through questions from MedQA, where the task is to select the most likely diagnosis. We introduce the Frequency-Based Probabilistic Ranker (FBPR), a lightweight method that scores options with a smoothed Naive Bayes over concept-diagnosis co-occurrence statistics from a large corpus. When co-occurrence statistics were sourced from the pretraining corpora for OLMo and Llama, FBPR achieves comparable performance to the corresponding LLMs pretrained on that same corpus. Direct LLM inference and FBPR largely get different questions correct, with an overlap only slightly above random chance, indicating complementary strengths of each method. These findings highlight the continued value of explicit probabilistic baselines: they provide a meaningful performance reference point and a complementary signal for potential hybridization. While the performance of LLMs seems to be driven by a mechanism other than simple frequency aggregation, we show that an approach similar to the historically grounded, low-complexity expert systems still accounts for a substantial portion of benchmark performance.

arXiv:2512.06393v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance on many natural language tasks, yet their generalisation under structured perturbations of logical rule systems remains insufficiently characterised. We present a controlled evaluation framework that probes reasoning reliability through four stress tests: (1) rule deletion, removing redundant versus essential rules from a multi-step inference chain; (2) contradictory evidence injection; (3) logic-preserving rewrites based on equivalence laws (contraposition, double negation, implication-to-disjunction, De Morgan, identity, and commutativity); and (4) multi-law equivalence stacking that composes 2–5 transformations. Across three representative model families — BERT, Qwen2, and LLaMA-like models — all models attain Acc$=1.0000$ on the base split and show no degradation under redundant rule deletion. In contrast, essential rule deletion yields a pronounced decrease to near-chance performance, and injecting explicit contradictions reduces accuracy to 0.0000. Under logic-preserving rewrites, accuracy is largely preserved for single-law transformations with only small degradations in a few cases, whereas multi-law stacking exposes model-dependent sensitivity: BERT matches the base condition, TinyLlama shows only marginal degradation, and Qwen2 exhibits a substantial drop. Overall, the results indicate that contemporary LLMs are generally stable under semantic-preserving reformulations, yet remain brittle to missing or inconsistent evidence and may degrade under composed logical transformations depending on the model family. The proposed framework provides a concise diagnostic tool for isolating these failure modes and for evaluating logical generalisation beyond surface-form variation.

arXiv:2512.11502v1 Announce Type: new Abstract: We present a new Hebrew medical language model designed to extract structured clinical timelines from electronic health records, enabling the construction of patient journeys. Our model is based on DictaBERT 2.0 and continually pre-trained on over five million de-identified hospital records. To evaluate its effectiveness, we introduce two new datasets — one from internal medicine and emergency departments, and another from oncology — annotated for event temporal relations. Our results show that our model achieves strong performance on both datasets. We also find that vocabulary adaptation improves token efficiency and that de-identification does not compromise downstream performance, supporting privacy-conscious model development. The model is made available for research use under ethical restrictions.

arXiv:2507.05578v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide range of tasks, yet they also exhibit memorization of their training data. This phenomenon raises critical questions about model behavior, privacy risks, and the boundary between learning and memorization. Addressing these concerns, this paper synthesizes recent studies and investigates the landscape of memorization, the factors influencing it, and methods for its detection and mitigation. We explore key drivers, including training data duplication, training dynamics, and fine-tuning procedures that influence data memorization. In addition, we examine methodologies such as prefix-based extraction, membership inference, and adversarial prompting, assessing their effectiveness in detecting and measuring memorized content. Beyond technical analysis, we also explore the broader implications of memorization, including the legal and ethical implications. Finally, we discuss mitigation strategies, including data cleaning, differential privacy, and post-training unlearning, while highlighting open challenges in balancing the need to minimize harmful memorization with model utility. This paper provides a comprehensive overview of the current state of research on LLM memorization across technical, privacy, and performance dimensions, identifying critical directions for future work.