January 2026

arXiv:2601.14280v1 Announce Type: new Abstract: Hallucinations in large language models (LLMs), defined as fluent yet incorrect or incoherent outputs, pose a significant challenge to the automatic generation of educational multiple-choice questions (MCQs). We identified four key hallucination types in MCQ generation: reasoning inconsistencies, insolvability, factual errors, and mathematical errors. To address this, we propose a hallucination-free multi-agent generation framework that breaks down MCQ generation into discrete, verifiable stages. Our framework utilizes both rule-based and LLM-based detection agents, as […]

Ver mais

arXiv:2601.14279v1 Announce Type: new Abstract: We investigate learned KV cache compression through Speculative Importance Prediction (SIP), a 1.7M parameter non-query-aware scorer that predicts token importance from KV representations alone. Despite architectural sophistication (multi-horizon lookahead, cross-attention), SIP does not outperform simple baselines, including random selection, across 5 seeds, 4 retention levels, and 3 tasks. Key findings: (1) position-based heuristics (keep first 4 + last N tokens) match or exceed learned approaches; (2) prefill attention provides equivalent signal to complex […]

Ver mais

arXiv:2601.14277v1 Announce Type: new Abstract: Quantization is a practical technique for making large language models easier to deploy by reducing the precision used to store and operate on model weights. This can lower memory use and improve runtime feasibility on constrained hardware, which is especially relevant for users running models locally. Quantization in llama.cpp enables large language models to run on commodity hardware, but available formats are often evaluated inconsistently, making it hard to choose among schemes. We […]

Ver mais

arXiv:2601.14275v1 Announce Type: new Abstract: Effective cooperation is pivotal in distributed learning for multi-agent systems, where the interplay between the quantity and quality of the machine learning models is crucial. This paper reveals the irrationality of indiscriminate inclusion of all models on agents for joint prediction, highlighting the imperative to prioritize quality over quantity in cooperative learning. Specifically, we present the first selective online learning framework for distributed Gaussian process (GP) regression, namely distributed error-informed GP (EIGP), that […]

Ver mais

arXiv:2601.14274v1 Announce Type: new Abstract: Multimodal emotion recognition in conversation (MERC) requires representations that effectively integrate signals from multiple modalities. These signals include modality-specific cues, information shared across modalities, and interactions that emerge only when modalities are combined. In information-theoretic terms, these correspond to emph{unique}, emph{redundant}, and emph{synergistic} contributions. An ideal representation should leverage all three, yet achieving such balance remains challenging. Recent advances in contrastive learning and augmentation-based methods have made progress, but they often overlook the […]

Ver mais

arXiv:2601.14271v1 Announce Type: new Abstract: Modern data systems must support accountability across persistent legal, political, and analytic disagreement. This requirement imposes strict constraints on the design of any ontology intended to function as a shared substrate. We establish an impossibility result for ontological neutrality: neutrality, understood as interpretive non-commitment and stability under incompatible extensions, is incompatible with the inclusion of causal or normative commitments at the foundational layer. Any ontology that asserts causal or deontic conclusions as ontological […]

Ver mais

arXiv:2601.14270v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities to solve problems requiring multiple reasoning steps, yet the internal mechanisms enabling such capabilities remain elusive. Unlike existing surveys that primarily focus on engineering methods to enhance performance, this survey provides a comprehensive overview of the mechanisms underlying LLM multi-step reasoning. We organize the survey around a conceptual framework comprising seven interconnected research questions, from how LLMs execute implicit multi-hop reasoning within hidden activations to […]

Ver mais

arXiv:2601.14269v1 Announce Type: new Abstract: Large language models (LLMs) have been widely used for mental health support. However, current safety evaluations in this field are mostly limited to detecting whether LLMs output prohibited words in single-turn conversations, neglecting the gradual erosion of safety boundaries in long dialogues. Examples include making definitive guarantees, assuming responsibility, and playing professional roles. We believe that with the evolution of mainstream LLMs, words with obvious safety risks are easily filtered by their underlying […]

Ver mais

arXiv:2601.14268v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used in medicine and clinical workflows, yet we know little about their decision and affective profiles. Taking a historically informed outlook on the future, we treated successive OpenAI models as an evolving lineage and compared them with humans in a gambling task with repeated happiness ratings. Computational analyses showed that some aspects became more human-like: newer models took more risks and displayed more human-like patterns of Pavlovian […]

Ver mais

arXiv:2601.14267v1 Announce Type: new Abstract: Biomedical evidence synthesis relies on accurate extraction of methodological, laboratory, and outcome variables from full-text research articles, yet these variables are embedded in complex scientific PDFs that make manual abstraction time-consuming and difficult to scale. Existing document AI systems remain limited by OCR errors, long-document fragmentation, constrained throughput, and insufficient auditability for high-stakes synthesis. We present a schema-constrained AI extraction system that transforms full-text biomedical PDFs into structured, analysis-ready records by explicitly restricting […]

Ver mais