Papers by Seonjeong Hwang
Can LLMs Estimate Cognitive Complexity of Reading Comprehension Items? (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for estimating the cognitive complexity of reading comprehension items are expensive, time-consuming, and subject to rater variability. |
| Approach: | They propose to use two dimensions to estimate cognitive complexity of RC items to focus on evidence Scope and transformation level to estimate the cognitive complexity. |
| Outcome: | The proposed models can estimate the cognitive complexity of items by focusing on two dimensions—Evidence Scope and Transformation Level—that indicate the degree of cognitive burden involved in reasoning about the answer. |
Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing models that generate complex questions do not explain reasoning process behind generated multi-hop questions. |
| Approach: | They propose an end-to-end question rewriting model that increases question complexity through sequential rewrite. |
| Outcome: | The proposed model generates complex questions that require multi-step reasoning over multiple documents. |
Why Do Multilingual Reasoning Gaps Emerge in Reasoning Language Models? (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent reasoning language models (RLMs) achieve strong performance on complex reasoning tasks, yet they still exhibit a multilingual reasoning gap. |
| Approach: | They propose a strategy that incorporates an English translation into the initial reasoning trace when an understanding failure is detected. |
| Outcome: | The proposed strategy incorporates an English translation into the initial reasoning trace when an understanding failure is detected. |
Conversational QA Dataset Generation with Answer Revision (2022.coling-1)
Copied to clipboard
| Challenge: | Existing frameworks for conversational question-answer generation generate a large-scale dataset based on input passages. |
| Approach: | They propose a conversational question-answer generation framework that extracts question-worthy phrases from passages and generates corresponding questions considering previous conversations. |
| Outcome: | The proposed framework improves the quality of synthetic data and can be used for domain adaptation of conversational question answering. |
Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing approaches to extend semantic parsing (SP) beyond English are challenging due to the complex slot alignment step after translation. |
| Approach: | They propose a method to enhance cross-lingual transfer for SP by utilizing mPLMs. |
| Outcome: | The proposed method synthesizes target language utterances from source meaning representations while maintaining high slot value alignment rates. |
KoBLEX: Open Legal Question Answering with Multi-hop Reasoning (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated remarkable performances in general domains and are now extending into the expert domain of law. |
| Approach: | They propose a Korean Benchmark for Legal EXplainable QA (KoBLEX) that evaluates provision-grounded, multi-hop legal reasoning. |
| Outcome: | The proposed method outperforms baselines and shows a high correlation with human judgments. |
MiLQ: Benchmarking IR Models for Bilingual Web Search with Mixed Language Queries (2025.emnlp-main)
Copied to clipboard
| Challenge: | Information Retrieval (IR) research on mixed-language queries remains sparse and outdated. |
| Approach: | They propose a test set for mixed-language queries that is realistic and preferred by bilingual speakers. |
| Outcome: | The proposed benchmarks show that multilingual IR models perform moderately on MiLQ and inconsistently across native, English, and mixed-language queries. |
Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing automatic question generation datasets focus on English, resulting in data gaps for other languages. |
| Approach: | They propose a cross-lingual transfer method that allows models to generate questions in low-resource languages. |
| Outcome: | The proposed method outperforms other models and achieves comparable performance across languages. |
A Multi-Agent Framework for Feature-Constrained Difficulty Control in Reading Comprehension Item Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for difficulty-controlled reading comprehension item generation rely on a single agent prompting approach. |
| Approach: | They propose a multi-agent framework for Feature-constrained Item Generation where multiple LLM agents collaborate to generate and iteratively revise items based on intended constraints. |
| Outcome: | The proposed method generates items with monotonically increasing difficulty at higher rates than baselines. |
Difficulty-Controllable Cloze Question Distractor Generation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing methods for generating high-quality distractors lack adaptability and control over difficulty levels. |
| Approach: | They propose a two-way distractor generation process to generate plausible distractors using an ensemble QA system and a multitask learning strategy to train a difficulty-controllable generation model. |
| Outcome: | The proposed method significantly outperforms GPT-4o in aligning distractor difficulty with human perception. |
Multi-Type Conversational Question-Answer Generation with Closed-ended and Unanswerable Questions (2022.aacl-short)
Copied to clipboard
| Challenge: | Conversational question answering (CQA) aims to answer a question based on a given passage and previous conversation. |
| Approach: | They propose a method to synthesize data for CQA with various question types . they propose 'hierarchical answerability classification' module that improves quality of synthetic data while acquiring unanswerable questions. |
| Outcome: | The proposed framework improves quality of synthetic data while acquiring unanswerable questions. |