Papers by Nayeon Lee
Mitigating Framing Bias with Polarity Minimization Loss (2023.findings-emnlp)
Copied to clipboard
| Challenge: | polarity is a pervasive problem in modern media, misleading the understanding of what really happened via a skewed selection of information and language. |
| Approach: | They propose a loss function that encourages the model to minimize the polarity difference between the skewed input articles to reduce framing bias. |
| Outcome: | The proposed loss improves the model's ability to map polarity ends bidirectionally. |
CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG (2026.findings-acl)
Copied to clipboard
| Challenge: | Multilingual retrieval-augmented generation is inadequate for culturally grounded queries . Across two cultural QA benchmarks, CORAL achieves a 3.58%p accuracy improvement on low-resource languages . |
| Approach: | They propose a multilingual retrieval-augmented generation approach that enables iterative refinement of both the retrieval space and the retrieving probe based on the quality of the evidence. |
| Outcome: | Using CORAL, researchers find that culturally grounded queries can be improved . if retrieved documents are insufficient, the system reselects them and rewrites the query . |
Break it Down into BTS: Basic, Tiniest Subword Units for Korean (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing word embeddings for Korean use the internal structure of words with subword information to improve the quality of word representations. |
| Approach: | They introduce Basic, Tiniest Subword (BTS) units for Korean language that are inspired by Hangeul, the Korean writing system. |
| Outcome: | The proposed framework outperforms the state-of-the-art Korean word embedding by 11.8% on all intrinsic and extrinsic tasks. |
FINEST: Improving LLM Responses to Sensitive Topics Through Fine-Grained Evaluation (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing evaluation frameworks lack systematic methods to identify weaknesses in LLMs . Existing methods to evaluate LLM responses to sensitive topics are lacking . |
| Approach: | They propose a FINE-grained response evaluation taxonomy for sensitive topics that breaks down helpfulness and harmlessness into errors across three main categories: Content, Logic, and Appropriateness. |
| Outcome: | The proposed model outperforms refinement without guidance on Korean-sensitive questions . FINEST significantly improves the model responses across all three categories . |
Towards Mitigating LLM Hallucination via Self Reflection (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models have shown promise for generative and knowledge-intensive tasks including question-answering (QA) but the practical deployment still faces challenges, notably the issue of “hallucination”, where models generate plausible-sounding but unfaithful or nonsensical information. |
| Approach: | They propose a self-reflection methodology that incorporates knowledge acquisition and answer generation to address the issue of "hallucination" they use a set of LLMs to generate a more accurate and factually accurate answer. |
| Outcome: | The proposed approach improves factuality, consistency, and entailment of the generated answers. |
Towards Few-shot Fact-Checking via Perplexity (2021.naacl-main)
Copied to clipboard
| Challenge: | Recent studies have shown that pre-trained language models can perform few-shot learning for various downstream tasks, such as question answering and machine translation. |
| Approach: | They propose a method to leverage the powerful transfer learning ability of a language model via a perplexity score to learn few-shot for the fact-checking task. |
| Outcome: | The proposed method outperforms the Major Class baseline by 10% on the F1-Macro metric across multiple datasets. |
Exploring Cross-Cultural Differences in English Hate Speech Annotations: From Dataset Construction to Analysis (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing datasets for hate speech detection neglect the cultural diversity within a single language. |
| Approach: | They propose a CR**oss-cultural **E**nglish **Hate* speech dataset that uses culturally hateful keywords to identify posts from four countries plus the United States. |
| Outcome: | The proposed dataset shows that only 56.2% of the posts in CREHate achieve consensus among all countries, with the highest pairwise label difference rate of 26%. |
Improving Large-Scale Fact-Checking using Decomposable Attention Models and Lexical Tagging (D18-1)
Copied to clipboard
| Challenge: | Existing pipelines for fact-checking of textual sources are limited . fact- checking of text sources requires a large knowledge base to extract relevant information . |
| Approach: | They propose a neural ranker that dynamically selects sentences to improve evidence retrieval . they incorporate lexical tagging methods into the pipeline framework to simplify the tasks . |
| Outcome: | The proposed model outperforms the existing TF-IDF method on a large-scale fact extraction and verification dataset with speedup. |
Measuring Political Bias in Large Language Models: What Is Said and How It Is Said (2024.acl-long)
Copied to clipboard
| Challenge: | Existing benchmarks and measures focus on gender and racial biases, but political bias exists in LLMs and can lead to polarization and other harms in downstream applications. |
| Approach: | They propose to analyze the content and style of LLMs generated by political issues and propose a framework that can be scalable to other topics. |
| Outcome: | The proposed framework is easily scalable to other topics and is explainable. |
Evaluating Parameter Efficient Learning for Generation (2022.emnlp-main)
Copied to clipboard
Peng Xu, Mostofa Patwary, Shrimai Prabhumoye, Virginia Adams, Ryan Prenger, Wei Ping, Nayeon Lee, Mohammad Shoeybi, Bryan Catanzaro
| Challenge: | Parameter efficient learning methods (PERMs) are gaining attention for their ability to adapt to a downstream task. |
| Approach: | They propose to use parameter efficient learning methods to improve model adaptation . they compare in-domain evaluations and generalizations to unseen domains and new datasets . |
| Outcome: | The proposed method outperforms finetuning and PERMs in in-domain evaluations. |
NeuS: Neutral Multi-News Summarization for Mitigating Framing Bias (2022.naacl-main)
Copied to clipboard
| Challenge: | a new task is proposed to reduce media news framing bias by generating a neutral summary from multiple news articles of the varying political leanings. |
| Approach: | They propose a task that generates a neutral summary from multiple news articles . they find title provides a good signal for framing bias and propose metric and model . |
| Outcome: | The proposed task can neutralize news content in hierarchical order from title to article . scalability remains a bottleneck due to the time-consuming human labor needed for composing the roundup . |
RHO: Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing knowledge-grounded dialogue systems generate accurate and informative responses, but they are prone to hallucination problems. |
| Approach: | They propose a method to generate hallucinated responses using knowledge graphs . they propose local knowledge grounding to combine textual embeddings with corresponding KG embeddments . a global knowledge ground technique is also proposed to equip RHO with multi-hop reasoning abilities . |
| Outcome: | The proposed approach outperforms state-of-the-art methods on automatic and human evaluation by a large margin. |
Polishing Every Facet of the GEM: Testing Linguistic Competence of LLMs and Humans in Korean (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies have focused on linguistic competence of language models with grammatical knowledge. |
| Approach: | They propose to use grammar as a measurable proxy to assess linguistic competence of large language models (LLMs) . |
| Outcome: | The proposed model aims to assess the linguistic competence of large language models (LLMs) and humans in Korean. |
On Unifying Misinformation Detection (2021.naacl-main)
Copied to clipboard
| Challenge: | On any given day, 2.5 quintillion bytes of information are created on the Internet, a figure that is only expected to increase in the coming years. |
| Approach: | They propose a general-purpose misinformation model that jointly models multiple domains of misinformation with a single, unified setup. |
| Outcome: | The proposed model is useful for few-shot learning of unseen misinformation tasks/datasets and generalizability to unseense events. |