Despite their strong performance, large language models (LLMs) face challenges in real-world application of lexical simplification (LS), particularly in privacy-sensitive and resource-constrained environments. Moreover, since vulnerable user groups (e.g., people with disabilities) are one of the key target groups of this technology, it is crucial to ensure the safety and correctness of the output of LS systems. To address these issues, we propose an efficient framework for LS systems that utilizes small LLMs deployable in local environments. Within this framework, we explore knowledge distillation with synthesized data and in-context learning as baselines. Our experiments in five languages evaluate model outputs both automatically and manually. Our manual analysis reveals that while knowledge distillation boosts automatic metric scores, it also introduces a safety trade-off by increasing harmful simplifications. Importantly, we find that the model’s output probability is a useful signal for detecting harmful simplifications. Leveraging this, we propose a filtering strategy that suppresses harmful simplifications while largely preserving beneficial ones. This work establishes a benchmark for efficient and safe LS with small LLMs. It highlights the key trade-offs between performance, efficiency, and safety, and demonstrates a promising approach for safe real-world deployment.

The TSAR 2025 Shared Task on Readability-Controlled Text Simplification focuses on simplifying English paragraphs written at an advanced level (B2 or higher) and rewriting them to target CEFR levels (A2 or B1). The challenge is to reduce linguistic complexity without sacrificing coherence or meaning. We developed three complementary approaches based on large language models (LLMs). The first approach (Run 1) generates a diverse set of paragraph-level simplifications. It then applies filters to enforce CEFR alignment, preserve meaning, and encourage diversity, and finally selects the candidates with the lowest perceived risk. The second (Run 2) performs simplification at the sentence level, combining structured prompting, coreference resolution, and explainable AI techniques to highlight influential phrases, with candidate selection guided by automatic and LLM-based judges. The third hybrid approach (Run 3) integrates both strategies by pooling paragraph- and sentence-level simplifications, and subsequently applying the identical filtering and selection architecture used in Run 1. In the official TSAR evaluation, the hybrid system ranked 2nd overall, while its component systems also achieved competitive results.

We report the findings of the 2024 Multilingual Lexical Simplification Pipeline shared task. We released a new dataset comprising 5,927 instances of lexical complexity prediction and lexical simplification on common contexts across 10 languages, split into trial (300) and test (5,627). 10 teams participated across 2 tracks and 10 languages with 233 runs evaluated across all systems. Five teams participated in all languages for the lexical complexity prediction task and 4 teams participated in all languages for the lexical simplification task. Teams employed a range of strategies, making use of open and closed source large language models for lexical simplification, as well as feature-based approaches for lexical complexity prediction. The highest scoring team on the combined multilingual data was able to obtain a Pearson’s correlation of 0.6241 and an ACC@1@Top1 of 0.3772, both demonstrating that there is still room for improvement on two difficult sub-tasks of the lexical simplification pipeline.

We present preliminary findings on the MultiLS dataset, developed in support of the 2024 Multilingual Lexical Simplification Pipeline (MLSP) Shared Task. This dataset currently comprises of 300 instances of lexical complexity prediction and lexical simplification across 10 languages. In this paper, we (1) describe the annotation protocol in support of the contribution of future datasets and (2) present summary statistics on the existing data that we have gathered. Multilingual lexical simplification can be used to support low-ability readers to engage with otherwise difficult texts in their native, often low-resourced, languages.

The tasks of lexical complexity prediction (LCP) and complex word identification (CWI) commonly presuppose that difficult-to-understand words are shared by the target population. Meanwhile, personalization methods have also been proposed to adapt models to individual needs. We verify that a recent Japanese LCP dataset is representative of its target population by partially replicating the annotation. By another reannotation we show that native Chinese speakers perceive the complexity differently due to Sino-Japanese vocabulary. To explore the possibilities of personalization, we compare competitive baselines trained on the group mean ratings and individual ratings in terms of performance for an individual. We show that the model trained on a group mean performs similarly to an individual model in the CWI task, while achieving good LCP performance for an individual is difficult. We also experiment with adapting a finetuned BERT model, which results only in marginal improvements across all settings.

The user-dependency of Text Simplification makes its evaluation obscure. A targeted evaluation dataset clarifies the purpose of simplification, though its specification is hard to define. We built JADES (JApanese Dataset for the Evaluation of Simplification), a text simplification dataset targeted at non-native Japanese speakers, according to public vocabulary and grammar profiles. JADES comprises 3,907 complex-simple sentence pairs annotated by an expert. Analysis of JADES shows that wide and multiple rewriting operations were applied through simplification. Furthermore, we analyzed outputs on JADES from several benchmark systems and automatic and manual scores of them. Results of these analyses highlight differences between English and Japanese in operations and evaluations.