OUNLP at TSAR 2025 Shared Task: Multi-Round Text Simplifier via Code Generation

• URL: http://arxiv.org/abs/2511.04495v1
• Date: Thu, 06 Nov 2025 16:16:32 GMT
• Title: OUNLP at TSAR 2025 Shared Task: Multi-Round Text Simplifier via Code Generation
• Authors: Cuong Huynh, Jie Cao,
• Abstract summary: This paper describes the OUNLP system submitted to the TSAR-2025 Shared Task (Alva-Manchego et al., 2025)<n>It is designed for readability-controlled text simplification using LLM-prompting-based generation.
• Score: 3.117899569620301
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This paper describes the OUNLP system submitted to the TSAR-2025 Shared Task (Alva-Manchego et al., 2025), designed for readability-controlled text simplification using LLM-prompting-based generation. Based on the analysis of prompt-based text simplification methods, we discovered an interesting finding that text simplification performance is highly related to the gap between the source CEFR (Arase et al., 2022) level and the target CEFR level. Inspired by this finding, we propose two multi-round simplification methods and generate them via GPT-4o: rule-based simplification (MRS-Rule) and jointly rule-based LLM simplification (MRS-Joint). Our submitted systems ranked 7 out of 20 teams. Later improvements with MRS-Joint show that taking the LLM simplified candidates as the starting point could further boost the multi-round simplification performance.

Related papers

• Rethinking On-policy Optimization for Query Augmentation [49.87723664806526]
  We present the first systematic comparison of prompting-based and RL-based query augmentation across diverse benchmarks.<n>We introduce a novel hybrid method, On-policy Pseudo-document Query Expansion (OPQE), which learns to generate a pseudo-document that maximizes retrieval performance.
  arXiv  Detail & Related papers  (2025-10-20T04:16:28Z)
• Facilitating Cognitive Accessibility with LLMs: A Multi-Task Approach to Easy-to-Read Text Generation [2.5978291328554373]
  Easy-to-Read (ETR) initiative offers framework for making content accessible to the neurodivergent population.<n>We investigate the potential of large language models (LLMs) to automate the generation of ETR content.<n>We propose a multi-task learning (MTL) approach that trains models jointly on text summarization, text simplification, and ETR generation.
  arXiv  Detail & Related papers  (2025-10-01T08:44:05Z)
• Hallucination Detection and Mitigation in Scientific Text Simplification using Ensemble Approaches: DS@GT at CLEF 2025 SimpleText [0.0]
  We describe our methodology for the CLEF 2025 SimpleText Task 2, which focuses on detecting and evaluating creative generation and information distortion.<n>Our solution integrates multiple strategies: we construct an ensemble framework that leverages BERT-based classifier, semantic similarity measure, natural language inference model, and large language model.<n>For grounded generation, we employ an LLM-based post-editing system that revises simplifications based on the original input texts.
  arXiv  Detail & Related papers  (2025-08-15T21:57:27Z)
• LLM-Guided Planning and Summary-Based Scientific Text Simplification: DS@GT at CLEF 2025 SimpleText [0.0]
  We present our approach for the CLEF 2025 SimpleText Task 1, which addresses both sentence-level and document-level scientific text simplification.<n>For sentence-level simplification, our methodology employs large language models (LLMs) to first generate a structured plan, followed by plan-driven simplification of individual sentences.<n>At the document level, we leverage LLMs to produce concise summaries and subsequently guide the simplification process using these summaries.
  arXiv  Detail & Related papers  (2025-08-15T21:44:52Z)
• Distilling Transitional Pattern to Large Language Models for Multimodal Session-based Recommendation [67.84581846180458]
  Session-based recommendation (SBR) predicts the next item based on anonymous sessions.<n>Recent Multimodal SBR methods utilize simplistic pre-trained models for modality learning but have limitations in semantic richness.<n>We propose a multimodal LLM-enhanced framework TPAD, which extends a distillation paradigm to decouple and align transitional patterns for promoting MSBR.
  arXiv  Detail & Related papers  (2025-04-13T07:49:08Z)
• Progressive Document-level Text Simplification via Large Language Models [19.57555397986868]
  Long document-level simplification (DS) is still relatively unexplored.<n>We propose a progressive simplification method (ProgDS) by hierarchically decomposing the task.
  arXiv  Detail & Related papers  (2025-01-07T15:14:37Z)
• Blending LLMs into Cascaded Speech Translation: KIT's Offline Speech Translation System for IWSLT 2024 [61.189875635090225]
  Large Language Models (LLMs) are currently under exploration for various tasks, including Automatic Speech Recognition (ASR), Machine Translation (MT), and even End-to-End Speech Translation (ST)
  arXiv  Detail & Related papers  (2024-06-24T16:38:17Z)
• DECIDER: A Dual-System Rule-Controllable Decoding Framework for Language Generation [57.07295906718989]
  Constrained decoding approaches aim to control the meaning or style of text generated by pre-trained large language (Ms also PLMs) for various tasks at inference time.<n>These methods often guide plausible continuations by greedily and explicitly selecting targets.<n>Inspired by cognitive dual-process theory, we propose a novel decoding framework DECIDER.
  arXiv  Detail & Related papers  (2024-03-04T11:49:08Z)
• Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting [65.00288634420812]
  Pairwise Ranking Prompting (PRP) is a technique to significantly reduce the burden on Large Language Models (LLMs) Our results are the first in the literature to achieve state-of-the-art ranking performance on standard benchmarks using moderate-sized open-sourced LLMs.
  arXiv  Detail & Related papers  (2023-06-30T11:32:25Z)
• Guiding Large Language Models via Directional Stimulus Prompting [114.84930073977672]
  We introduce Directional Stimulus Prompting, a novel framework for guiding black-box large language models (LLMs) toward specific desired outputs. Instead of directly adjusting LLMs, our method employs a small tunable policy model to generate an auxiliary directional stimulus prompt for each input instance.
  arXiv  Detail & Related papers  (2023-02-22T17:44:15Z)
• MANTIS at TSAR-2022 Shared Task: Improved Unsupervised Lexical Simplification with Pretrained Encoders [31.64341800095214]
  We present our contribution to the TSAR-2022 Shared Task on Lexical Simplification of the EMNLP 2022 Workshop on Text Simplification, Accessibility, and Readability. Our approach builds on and extends the unsupervised lexical simplification system with pretrained encoders (LSBert) system. Our best-performing system improves LSBert by 5.9% accuracy and second place out of 33 ranked solutions.
  arXiv  Detail & Related papers  (2022-12-19T20:57:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.