Recent reasoning-focused large language models (LLMs) (e.g., GPT-o1 and DeepSeek-R1) combine chain-of-thought prompting with reinforcement learning to generate explicit, multi-step derivations. However, their practical advantages over standard instruction-tuned models remain underexplored. In this article, we present a comprehensive empirical study to address these gaps. We compare reasoning-focused and non-reasoning LLMs across several critical dimensions: (1) their performance on mathematical and general reasoning benchmarks; (2) their generalization capabilities across 30 sub-disciplines spanning six scientific domains; (3) the qualitative and quantitative differences in their underlying solution processes; and (4) the impact of model compression via distillation on core reasoning capabilities. Crucially, to reliably conduct our in-depth process analysis, we address the critical issue of LLM-as-a-Judge reliability by proposing and validating a multi-level evaluation framework against human experts. Our experimental results demonstrate that reasoning-focused models significantly outperform non-reasoning counterparts on logic-intensive tasks such as mathematics and physics, while the latter remain competitive on factual or observational problems (e.g., biology, geography). Specifically, our validated process analysis reveals distinct styles: DeepSeek-R1 generates more elaborate reasoning processes, correlating with greater effectiveness on harder tasks, despite potential redundancy. In contrast, GPT-o1 exhibits greater conciseness and frequently presents solutions with superior clarity and efficiency, particularly on simpler problems, while struggling with complex scenarios. Additionally, reasoning capabilities can be partially preserved through distillation, with distilled reasoning models consistently outperforming their non-reasoning counterparts across all domains. These findings provide new insights into when and how explicit reasoning contributes to LLM performance, offering practical guidance for model development and deployment.

This paper presents an overview of the ClinicalSkillQA 2026 shared task, which was organized with the BioNLP Workshop at ACL 2026. The goal of this shared task is to evaluate continuous perception and procedural reasoning in clinical skill assessment by requiring systems to reconstruct the correct temporal order of shuffled clinical key frames and generate rationales grounded in clinical workflow knowledge. The benchmark contains 200 test-only instances sampled from clinical skill videos, covering three emergency-care procedures. Each instance is annotated with the ground-truth temporal order and an expert-verified rationale. A total of seven teams participated in the task, collectively making 90 submissions, with four teams providing system description papers. Systems are evaluated using Task Accuracy, Pairwise Accuracy, and BERTScore, which measure exact sequence reconstruction, local temporal consistency, and rationale quality, respectively. In this paper, we describe the task setup, dataset construction, and evaluation criteria. We further summarize the methodologies adopted by participating teams and present a comprehensive analysis of the submitted systems. The official results suggest that current models still struggle with continuous perception and procedural reasoning, especially when they must integrate visual evidence, temporal structure, and clinical workflow knowledge.

Document Image Translation (DIT), which aims at translating documents in images from source language to the target, plays an important role in Document Intelligence. It requires a comprehensive understanding of document multi-modalities and a focused concentration on relevant textual regions during translation. However, most existing methods usually rely on the vanilla encoder-decoder paradigm, severely losing concentration on key regions that are especially crucial for complex-layout document translation. To tackle this issue, in this paper, we propose a new Query-Response DIT framework (QRDIT). QRDIT reformulates the DIT task into a parallel response/translation process of the multiple queries (i.e., relevant source texts), explicitly centralizing its focus toward the most relevant textual regions to ensure translation accuracy. A novel dynamic aggregation mechanism is also designed to enhance the text semantics in query features toward translation. Extensive experiments in four translation directions on three benchmarks demonstrate its state-of-the-art performance, showing significant translation quality improvements toward whole-page complex-layout document images.

Multimodal Large Language Models (MLLMs) have shown strong performance in document image tasks, especially Optical Character Recognition (OCR). However, they struggle with Document Image Machine Translation (DIMT), which requires handling both cross-modal and cross-lingual challenges. Previous efforts to enhance DIMT capability through Supervised Fine-Tuning (SFT) on the DIMT dataset often result in the forgetting of the model’s existing monolingual abilities, such as OCR. To address these challenges, we introduce a novel fine-tuning paradigm, named Synchronously Self-Reviewing (SSR) its OCR proficiency, inspired by the concept “Bilingual Cognitive Advantage”. Specifically, SSR prompts the model to generate OCR text before producing translation text, which allows the model to leverage its strong monolingual OCR ability while learning to translate text across languages. Comprehensive experiments demonstrate the proposed SSR learning helps mitigate catastrophic forgetting, improving the generalization ability of MLLMs on both OCR and DIMT tasks. The code will be released upon acceptance.

Machine learning (ML) has been successfully used as a prevalent approach to solving numerous NLP problems. However, the classic ML paradigm learns in isolation. That is, given a dataset, an ML algorithm is executed on the dataset to produce a model without using any related or prior knowledge. Although this type of isolated learning is very useful, it also has serious limitations as it does not accumulate knowledge learned in the past and use the knowledge to help future learning, which is the hallmark of human learning and human intelligence. Lifelong machine learning (LML) aims to achieve this capability. Specifically, it aims to design and develop computational learning systems and algorithms that learn as humans do, i.e., retaining the results learned in the past, abstracting knowledge from them, and using the knowledge to help future learning. In this tutorial, we will introduce the existing research of LML and to show that LML is very suitable for NLP tasks and has potential to help NLP make major progresses.