DeepSeek vs. o3-mini: How Well can Reasoning LLMs Evaluate MT and Summarization?

Reasoning-enabled large language models (LLMs) have recently demonstrated impressive performance in complex logical and mathematical tasks, yet their effectiveness in evaluating natural language generation remains unexplored. This study systematically compares reasoning-based LLMs (DeepSeek-R1 and OpenAI o3) with their non-reasoning counterparts across machine translation (MT) and text summarization (TS) evaluation tasks. We evaluate eight models across three architectural categories, including state-of-the-art reasoning models, their distilled variants (ranging from 8B to 70B parameters), and equivalent conventional, non-reasoning LLMs. Our experiments on WMT23 and SummEval benchmarks reveal that the benefits of reasoning capabilities are highly model and task-dependent: while OpenAI o3-mini models show consistent performance improvements with increased reasoning intensity, DeepSeek-R1 underperforms compared to its non-reasoning variant, with exception to certain aspects of TS evaluation. Correlation analysis demonstrates that increased reasoning token usage positively correlates with evaluation quality in o3-mini models. Furthermore, our results show that distillation of reasoning capabilities maintains reasonable performance in medium-sized models (32B) but degrades substantially in smaller variants (8B). This work provides the first comprehensive assessment of reasoning LLMs for NLG evaluation and offers insights into their practical use.

ACLSum: A New Dataset for Aspect-based Summarization of Scientific Publications

Extensive efforts in the past have been directed toward the development of summarization datasets. However, a predominant number of these resources have been (semi)-automatically generated, typically through web data crawling, resulting in subpar resources for training and evaluating summarization systems, a quality compromise that is arguably due to the substantial costs associated with generating ground-truth summaries, particularly for diverse languages and specialized domains. To address this issue, we present ACLSum, a novel summarization dataset carefully crafted and evaluated by domain experts. In contrast to previous datasets, ACLSum facilitates multi-aspect summarization of scientific papers, covering challenges, approaches, and outcomes in depth. Through extensive experiments, we evaluate the quality of our resource and the performance of models based on pretrained language models and state-of-the-art large language models (LLMs). Additionally, we explore the effectiveness of extractive versus abstractive summarization within the scholarly domain on the basis of automatically discovered aspects. Our results corroborate previous findings in the general domain and indicate the general superiority of end-to-end aspect-based summarization. Our data is released at https://github.com/sobamchan/aclsum.

ROUGE-K: Do Your Summaries Have Keywords?

Keywords, that is, content-relevant words in summaries play an important role in efficient information conveyance, making it critical to assess if system-generated summaries contain such informative words during evaluation. However, existing evaluation metrics for extreme summarization models do not pay explicit attention to keywords in summaries, leaving developers ignorant of their presence. To address this issue, we present a keyword-oriented evaluation metric, dubbed ROUGE-K, which provides a quantitative answer to the question of -- \textit{How well do summaries include keywords?} Through the lens of this keyword-aware metric, we surprisingly find that a current strong baseline model often misses essential information in their summaries. Our analysis reveals that human annotators indeed find the summaries with more keywords to be more relevant to the source documents. This is an important yet previously overlooked aspect in evaluating summarization systems. Finally, to enhance keyword inclusion, we propose four approaches for incorporating word importance into a transformer-based model and experimentally show that it enables guiding models to include more keywords while keeping the overall quality. Our code is released at https://github.com/sobamchan/rougek.

VADIS -- a VAriable Detection, Interlinking and Summarization system

The VADIS system addresses the demand of providing enhanced information access in the domain of the social sciences. This is achieved by allowing users to search and use survey variables in context of their underlying research data and scholarly publications which have been interlinked with each other.

Towards Automated Survey Variable Search and Summarization in Social Science Publications

Nowadays there is a growing trend in many scientific disciplines to support researchers by providing enhanced information access through linking of publications and underlying datasets, so as to support research with infrastructure to enhance reproducibility and reusability of research results. In this research note, we present an overview of an ongoing research project, named VADIS (VAriable Detection, Interlinking and Summarization), that aims at developing technology and infrastructure for enhanced information access in the Social Sciences via search and summarization of publications on the basis of automatic identification and indexing of survey variables in text. We provide an overview of the overarching vision underlying our project, its main components, and related challenges, as well as a thorough discussion of how these are meant to address the limitations of current information access systems for publications in the Social Sciences. We show how this goal can be concretely implemented in an end-user system by presenting a search prototype, which is based on user requirements collected from qualitative interviews with empirical Social Science researchers.

X-SCITLDR: Cross-Lingual Extreme Summarization of Scholarly Documents

The number of scientific publications nowadays is rapidly increasing, causing information overload for researchers and making it hard for scholars to keep up to date with current trends and lines of work. Consequently, recent work on applying text mining technologies for scholarly publications has investigated the application of automatic text summarization technologies, including extreme summarization, for this domain. However, previous work has concentrated only on monolingual settings, primarily in English. In this paper, we fill this research gap and present an abstractive cross-lingual summarization dataset for four different languages in the scholarly domain, which enables us to train and evaluate models that process English papers and generate summaries in German, Italian, Chinese and Japanese. We present our new X-SCITLDR dataset for multilingual summarization and thoroughly benchmark different models based on a state-of-the-art multilingual pre-trained model, including a two-stage `summarize and translate' approach and a direct cross-lingual model. We additionally explore the benefits of intermediate-stage training using English monolingual summarization and machine translation as intermediate tasks and analyze performance in zero- and few-shot scenarios.

ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System

This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Open-retrieval Question Answering (COQA). In this challenging scenario, given an input question the system has to gather evidence documents from a multilingual pool and generate from them an answer in the language of the question. We devised several approaches combining different model variants for three main components: Data Augmentation, Passage Retrieval, and Answer Generation. For passage retrieval, we evaluated the monolingual BM25 ranker against the ensemble of re-rankers based on multilingual pretrained language models (PLMs) and also variants of the shared task baseline, re-training it from scratch using a recently introduced contrastive loss that maintains a strong gradient signal throughout training by means of mixed negative samples. For answer generation, we focused on language- and domain-specialization by means of continued language model (LM) pretraining of existing multilingual encoders. Additionally, for both passage retrieval and answer generation, we augmented the training data provided by the task organizers with automatically generated question-answer pairs created from Wikipedia passages to mitigate the issue of data scarcity, particularly for the low-resource languages for which no training data were provided. Our results show that language- and domain-specialization as well as data augmentation help, especially for low-resource languages.