January 2026

arXiv:2601.09734v1 Announce Type: new Abstract: Hallucinations in Large Language Models (LLMs), defined as the generation of content inconsistent with facts or context, represent a core obstacle to their reliable deployment in critical domains. Current research primarily focuses on binary “detection” approaches that, while capable of identifying hallucinations, fail to provide interpretable and actionable feedback for model improvement, thus limiting practical utility. To address this limitation, a new research paradigm is proposed, shifting from “detection” to “diagnosis”. The Hallucination […]

Ver mais

arXiv:2601.09733v1 Announce Type: new Abstract: The construction of Supervised Fine-Tuning (SFT) datasets is a critical yet under-theorized stage in the post-training of Large Language Models (LLMs), as prevalent practices often rely on heuristic aggregation without a systematic understanding of how individual samples contribute to model performance. In this report, we propose a paradigm shift from ad-hoc curation to a closed-loop dataset engineering framework using OpenDataArena (ODA), which leverages value-anchored rankings and multi-dimensional analysis to transform value benchmarking into […]

Ver mais

arXiv:2601.09732v1 Announce Type: new Abstract: With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB) may mask fundamental alignment shortcomings. We introduce Semantic Affinity (SA), a bounded (between 0 and 1) metric measuring inter-lingual to intra-lingual spread ratio using cosine distance, combined with PHATE visualization in our Semanscope framework. Benchmarking 13 models across 4 datasets (52 experiments) reveals a three-tier structure: […]

Ver mais

arXiv:2601.09731v1 Announce Type: new Abstract: We introduce a multi-level analysis framework for examining semantic geometry in multilingual embeddings, implemented through Semanscope (a visualization tool that applies PHATE manifold learning across four linguistic levels). Analysis of diverse datasets spanning sub-character components, alphabetic systems, semantic domains, and numerical concepts reveals systematic geometric patterns and critical limitations in current embedding models. At the sub-character level, purely structural elements (Chinese radicals) exhibit geometric collapse, highlighting model failures to distinguish semantic from structural […]

Ver mais

arXiv:2601.09730v1 Announce Type: new Abstract: Clinical document metadata, such as document type, structure, author role, medical specialty, and encounter setting, is essential for accurate interpretation of information captured in clinical documents. However, vast documentation heterogeneity and drift over time challenge harmonization of document metadata. Automated extraction methods have emerged to coalesce metadata from disparate practices into target schema. This scoping review aims to catalog research on clinical document metadata extraction, identify methodological trends and applications, and highlight gaps. […]

Ver mais

arXiv:2601.09729v1 Announce Type: new Abstract: Financial reports and earnings communications contain large volumes of structured and semi structured information, making detailed manual analysis inefficient. Earnings conference calls provide valuable evidence about a firm’s performance, outlook, and strategic priorities. The manual analysis of lengthy call transcripts requires substantial effort and is susceptible to interpretive bias and unintentional error. In this work, we present a hybrid summarization framework that combines extractive and abstractive techniques to produce concise and factually reliable […]

Ver mais

arXiv:2601.09728v1 Announce Type: new Abstract: In recent years, using predefined agentic workflows to guide large language models (LLMs) for literature classification and review has become a research focus. However, writing research introductions is more challenging. It requires rigorous logic, coherent structure, and abstract summarization. Existing workflows often suffer from long reasoning chains, error accumulation, and reduced textual coherence. To address these limitations, we propose eliminating external agentic workflows. Instead, we directly parameterize their logical structure into the LLM. […]

Ver mais

arXiv:2601.09727v1 Announce Type: new Abstract: Cross-domain scientific synthesis requires connecting mechanistic explanations across fragmented literature, a capability that remains challenging for both retrieval-based systems and unconstrained language models. While recent work has applied large language models to scientific summarization and question answering, these approaches provide limited control over reasoning depth and structural grounding. We frame mechanistic synthesis as a graph-constrained multi-hop reasoning problem over literature-derived concept graphs. Given a scientific query and a compact, query-local corpus, SciNets constructs […]

Ver mais

arXiv:2601.09726v1 Announce Type: new Abstract: Large Language Models (LLMs) are often evaluated against ideals of perfect Bayesian inference, yet growing evidence suggests that their in-context reasoning exhibits systematic forgetting of past information. Rather than viewing this behavior as a limitation, we reinterpret forgetting as a functional cognitive mechanism. Drawing inspiration from human memory dynamics, we model LLM inference as a probabilistic memory process governed by exponential decay. We introduce a benchmark suite that evaluates temporal reasoning, concept drift […]

Ver mais

arXiv:2601.09725v1 Announce Type: new Abstract: Punctuation plays a critical role in resolving semantic and structural ambiguity in written language. Machine Translation (MT) systems are now widely applied across diverse domains and languages, including many low-resource settings. In this work, we focus on Marathi, a low- to middle-resource language. We introduce Vir=am, the first diagnostic benchmark for assessing punctuation robustness in English-to-Marathi machine translation, consisting of 54 manually curated, punctuation-ambiguous instances. We evaluate two primary strategies for enhancing reliability: […]

Ver mais