Today’s digest highlights how progress in language technology is increasingly tied not just to scale, but to how models are structured, evaluated, and deployed in real-world settings. Across the papers, a common thread is the push for more reliable behavior through clearer linguistic structure, better handling of ambiguity via interaction, and closer scrutiny of what supervised training actually teaches models. Another recurring theme is trustworthiness: from healthcare benchmarking to adversarial text manipulation, the work underscores that capability gains must be matched by robustness, interpretability, and safeguards against misuse.

Comparative Analysis of Large Language Models in Healthcare

Background: Large Language Models (LLMs) are transforming artificial intelligence applications in healthcare due to their ability to understand, generate, and summarize complex medical text. They offer valuable support to clinicians, researchers, and patients, yet their deployment in high-stakes clinical environments raises critical concerns regarding accuracy, reliability, and patient safety. Despite substantial attention in recent years, standardized benchmarking of LLMs for medical applications has been limited. Objective: This study addresses the need for a standardized comparative evaluation of LLMs in medical settings. Method: We evaluate multiple models, including ChatGPT, LLaMA, Grok, Gemini, and ChatDoctor, on core medical tasks such as patient note summarization and medical question answering, using the open-access datasets, MedMCQA, PubMedQA, and Asclepius, and assess performance through a combination of linguistic and task-specific metrics. Results: The results indicate that domain-specific models, such as ChatDoctor, excel in contextual reliability, producing medically accurate and semantically aligned text, whereas general-purpose models like Grok and LLaMA perform better in structured question-answering tasks, demonstrating higher quantitative accuracy. This highlights the complementary strengths of domain-specific and general-purpose LLMs depending on the medical task. Conclusion: Our findings suggest that LLMs can meaningfully support medical professionals and enhance clinical decision-making; however, their safe and effective deployment requires adherence to ethical standards, contextual accuracy, and human oversight in relevant cases. These results underscore the importance of task-specific evaluation and cautious integration of LLMs into healthcare workflows.

Think in Sentences: Explicit Sentence Boundaries Enhance Language Model's Capabilities

Researchers have explored different ways to improve large language models (LLMs)' capabilities via dummy token insertion in contexts. However, existing works focus solely on the dummy tokens themselves, but fail to leverage the inherent sentence-level structure of natural language. This is a critical oversight, as LLMs acquire linguistic capabilities through exposure to human-generated texts, which are inherently structured at the sentence level. Motivated by this gap, we propose an approach that inserts delimiters at sentence boundaries in LLM inputs, which not only integrates dummy tokens into the context, but also facilitates LLMs with sentence-by-sentence processing behavior during reasoning. Two concrete methods: (1). In-context learning and (2). Supervised fine-tuning are experimented using 7B models to 600B Deepseek-V3. Our results demonstrate consistent improvements across various tasks, with notable gains of up to 7.7\% on GSM8k and 12.5\% on DROP. Furthermore, the fine-tuned LLMs can incorporate sentence awareness evidenced by their internal representations. Our work establishes a simple yet effective technique for enhancing LLM's capabilities, offering promising directions for cognitive-inspired LLM enhancement paradigm.

ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification

The advancement of large language models (LLMs) has enhanced tabular question answering (Tabular QA), yet they struggle with open-domain queries exhibiting underspecified or uncertain expressions. To address this, we introduce the ODUTQA-MDC task and the first comprehensive benchmark to tackle it. This benchmark includes: (1) a large-scale ODUTQA dataset with 209 tables and 25,105 QA pairs; (2) a fine-grained labeling scheme for detailed evaluation; and (3) a dynamic clarification interface that simulates user feedback for interactive assessment. We also propose MAIC-TQA, a multi-agent framework that excels at detecting ambiguities, clarifying them through dialogue, and refining answers. Experiments validate our benchmark and framework, establishing them as a key resource for advancing conversational, underspecification-aware Tabular QA research.

Hijacking Text Heritage: Hiding the Human Signature through Homoglyphic Substitution

In what way could a data breach involving government-issued IDs such as passports, driver's licenses, etc., rival a random voluntary disclosure on a nondescript social-media platform? At first glance, the former appears more significant, and that is a valid assessment. The disclosed data could contain an individual's date of birth and address; for all intents and purposes, a leak of that data would be disastrous. Given the threat, the latter scenario involving an innocuous online post seems comparatively harmless--or does it? From that post and others like it, a forensic linguist could stylometrically uncover equivalent pieces of information, estimating an age range for the author (adolescent or adult) and narrowing down their geographical location (specific country). While not an exact science--the determinations are statistical--stylometry can reveal comparable, though noticeably diluted, information about an individual. To prevent an ID from being breached, simply sharing it as little as possible suffices. Preventing the leakage of personal information from written text requires a more complex solution: adversarial stylometry. In this paper, we explore how performing homoglyph substitution--the replacement of characters with visually similar alternatives (e.g., "h" $\texttt{[U+0068]}$ $\rightarrow$ "h" $\texttt{[U+04BB]}$)--on text can degrade stylometric systems.

Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models

Supervised Fine-Tuning (SFT) is the standard approach for adapting large language models (LLMs) to downstream tasks. However, we observe a persistent failure mode: even after convergence, models often fail to correctly reproduce a subset of their own supervised training data. We refer to this behavior as the Incomplete Learning Phenomenon(ILP). This paper presents the first systematic study of ILP in LLM fine-tuning. We formalize ILP as post-training failure to internalize supervised instances and demonstrate its prevalence across multiple model families, domains, and datasets. Through controlled analyses, we identify five recurrent sources of incomplete learning: (1) missing prerequisite knowledge in the pre-trained model, (2) conflicts between SFT supervision and pre-training knowledge, (3) internal inconsistencies within SFT data, (4) left-side forgetting during sequential fine-tuning, and (5) insufficient optimization for rare or complex patterns. We introduce a diagnostic-first framework that maps unlearned samples to these causes using observable training and inference signals, and study several targeted mitigation strategies as causal interventions. Experiments on Qwen, LLaMA, and OLMo2 show that incomplete learning is widespread and heterogeneous, and that improvements in aggregate metrics can mask persistent unlearned subsets. The findings highlight the need for fine-grained diagnosis of what supervised fine-tuning fails to learn, and why.