LLMs for Reading Assistance

Essential Readings

• BLESS: Benchmarking Large Language Models on Sentence Simplification (Kew et.al., 2023)
• Review on Neural Question Generation for Education Purposes (Al Farabi et.al., 2023)
• Trends, limitations and open challenges in automatic readability assessment research (Vajjala, 2022)
• Automatic text simplification for social good: Progress and challenges (Stajner, 2021)
• Problems in Current Text Simplification Research: New Data Can Help (Xu et.al., 2015)

Task: Automatic Readability Assessment

Surveys

• Computational assessment of text readability: A survey of current and future research (Collins-Thompson, 2014)

Methods

• Investigating Large Language Models for Complex Word Identification in Multilingual and Multidomain Setups (Smadu et.al., 2024)
• README++: Benchmarking Multilingual Language Models for Multi-Domain Readability Assessment(Naous et.al., 2024)
• FPT: Feature Prompt Tuning for Few-shot Readability Assessment (Wang et.al., 2024)
• Beyond Flesch-Kincaid:Prompt-based Metrics Improve Difficulty Classification of Educational Texts (Rooein et.al., 2024)
• Exploring hybrid approaches to readability: experiments on the complementarity between linguistic features and transformers(Wilkens et.al., 2024)
• Difficult for Whom? A Study of Japanese Lexical Complexity(Nohejl et.al., 2024)
• Prompt-based Learning for Text Readability Assessment (Lee and Lee, 2023)
• Multiattentive Recurrent Neural Network Architecture for Multilingual Readability Assessment (Azpiazu and Pera, 2019)
• Text readability assessment for second language learners (Xia et.al., 2016)

Evaluation

• Fine-Grained Prediction of Reading Comprehension from Eye Movements (Shubi et.al., 2024)
• On understanding the relation between expert annotations of text readability and target reader comprehension (Vajjala and Lucic, 2019)
• Towards grounding computational linguistic approaches to readability: Modeling reader-text interaction for easy and difficult texts (Vajjala et.al., 2016)
• Are Cohesive Features Relevant for Text Readability Evaluation?(Todirascu et.al., 2016)

Shared Tasks

• SemEval-2016 Task 11: Complex Word Identification (Paetzold and Specia, 2016)
• SemEval-2021 Task 1: Lexical Complexity Prediction(Shardlow et.al., 2021)

Corpora/Other Resources

• English: OneStopEnglish (Vajjala and Lucic, 2018), CommonLit Ease of Readability Corpus (Crossley et.al., 2021)
• German: TextComplexityDE (Naderi et.al., 2019)

Explainability/Interpretability

• Explainable AI in Language Learning: Linking Empirical Evidence and Theoretical Concepts in Proficiency and Readability Modeling of Portuguese (Ribeiro-Flucht et.al., 2024)
• “Geenmakkie”: Interpretable Classification and Simplification of Dutch Text Complexity (Hobo et.al., 2023)

Task: Automatic Text Simplification

Surveys

• Data-Driven Sentence Simplification: Survey and Benchmark(Alva-Manchego et.al., 2020)
• A survey of research on text simplification (Siddharthan, 2014)

Methods:

• ExpertEase: A Multi-Agent Framework for Grade-Specific Document Simplification with Large Language Models (Mo and Hu, 2024)
• Evaluating LLMs for Targeted Concept Simplification forDomain-Specific Texts (Asthana et.al., 2024)
• Edit-Constrained Decoding for Sentence Simplification (Zetsu et.al., 2024)
• Label Confidence Weighted Learning for Target-level Sentence Simplification (Qiu and Zhang, 2024)
• Elaborative Simplification for German-language Texts(Hewett et.al., 2024)
• An LLM-Enhanced Adversarial Editing System for Lexical Simplification(Tan et.al., 2024)
• On Simplification of Discharge Summaries in Serbian: Facing the Challenges(Zecevic et.al., 2024)
• DIMSIM: Distilled Multilingual Critics for Indic Text Simplification(Mondal et.al., 2024)
• Enhancing Sentence Simplification in Portuguese: Leveraging Paraphrases, Context, and Linguistic Features(Scalercio et.al., 2024)
• Analysing Zero-Shot Readability-Controlled Sentence Simplification(Barayan et.al., 2024)
• Measuring and Modifying the Readability of English Texts with GPT-4 (Trott et.al., 2024)
• Learning to Paraphrase Sentences to Different Complexity Levels(Chi et.al., 2023)
• MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases(Martin et.al., 2022)
• Keep It Simple: Unsupervised Simplification of Multi-Paragraph Text(Laban et.al., 2021)
• Optimizing statistical machine translation for text simplification(Xu et.al., 2016)
• Learning to simplify sentences with quasi-synchronous grammar and integer programming(Woodsend and Lapata, 2011)
• Automatic induction of rules for text simplification(Chandrasekar and Srinivas, 1997)

Evaluation:

• Do Text Simplification Systems Preserve Meaning? A Human Evaluation via Reading Comprehension (Agrawal and Carpuat, 2024)
• Digital Comprehensibility Assessment of Simplified Texts among Persons with Intellectual Disabilities
(Säuberli et.al., 2024)
• Linguistic Corpus Annotation for Automatic Text Simplification Evaluation (Cardon et.al., 2022)
• The (Un)Suitability of Automatic Evaluation Metrics for Text Simplification (Alva-Manchego et.al., 2021)
• Investigating Text Simplification Evaluation (Vásquez-Rodríguez et.al., 2021)

Shared Tasks

• The BEA 2024 Shared Task on the Multilingual Lexical Simplification Pipeline
• SemEval-2012 Task 1: English Lexical Simplification

Corpora/Other Resources

• Lexical Complexity Prediction and Lexical Simplification for Catalan and Spanish: Resource Creation, Quality Assessment, and Ethical Considerations(Saggion et.al., 2024)
• Language Resources in Spanish for Automatic Text Simplification across Domains (Moreno-Sandoval et.al., 2024)
• Text simplification datasets listing (Jan Trienes, 2024)
• CompLex-ZH: A New Dataset for Lexical Complexity Prediction in Mandarin and Cantonese (Qiu et.al., 2024)

Other Related Topics

• Considering Human Interaction and Variability in Automatic Text Simplification(Kim et.al., 2024)
• ARTS: Assessing Readability & Text Simplicity 🎨(Engelmann et.al., 2024)

Task: Automatic Question Generation

Surveys

• A systematic review of automatic question generation for educational purposes (Kurdi et.al., 2020)

Methods

• Improving Socratic Question Generation using Data Augmentation and Preference Optimization (Kumar and Lan, 2024)
• Improving Automated Distractor Generation for Math Multiple-choice Questions with Overgenerate-and-rank (Scarlatos et.al., 2024)
• Difficulty-Controllable Neural Question Generation for Reading Comprehension using Item Response Theory (Uto et.al., 2023)
• Comparing Neural Question Generation Architectures for Reading Comprehension (Perkoff et.al., 2023)
• Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages (Hwang et.al., 2023)

Evaluation

• How Good are Modern LLMs in Generating Relevant and High-Quality Questions at Different Bloom’s Skill Levels for Indian High School Social Science Curriculum? (Scaria et.al., 2024)
• Evaluating Reading Comprehension Exercises Generated by LLMs: A Showcase of ChatGPT in Education Applications (Xiao et.al., 2024)

Task: Other Applications

• Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation(Imperial et.al., 2024)
• LLMs as Academic Reading Companions: Extending HCI Through Synthetic Personae