Papers by Chan Young Park

15 papers
Subtle Risks, Critical Failures: A Framework for Diagnosing Physical Safety of LLMs for Embodied Decision Making (2025.emnlp-main)

Copied to clipboard

Challenge: Existing safety evaluations rely on coarse success rates and domain-specific setups, making it difficult to diagnose why and where these models fail.
Approach: They propose a framework for systematically evaluating the physical safety of LLMs in embodied decision making.
Outcome: The proposed framework assesses the physical safety of LLMs in embodied decision making.
Cross-Cultural Similarity Features for Cross-Lingual Transfer Learning of Pragmatically Motivated Tasks (2021.eacl-main)

Copied to clipboard

Challenge: a large amount of work on cross-lingual transfer learning focused on typological and genealogical similarities between languages.
Approach: They propose three features that capture cross-cultural similarities that manifest in linguistic patterns and quantify distinct aspects of language pragmatics.
Outcome: The proposed features capture cross-cultural similarities manifest in linguistic patterns and quantify aspects of language pragmatics.
Reasoning Up the Instruction Ladder for Controllable Language Models (2026.findings-acl)

Copied to clipboard

Challenge: Current models struggle to balance competing directives, causing conflicting instructions.
Approach: They propose to reframe instruction hierarchy resolution as a reasoning task . they use a training dataset to enable this capability by transferring general reasoning capabilities to instruction prioritization .
Outcome: The proposed method improves on safety-critical scenarios beyond the training distribution and jailbreaks.
CulturalBench: A Robust, Diverse and Challenging Benchmark for Measuring LMs’ Cultural Knowledge Through Human-AI Red-Teaming (2025.acl-long)

Copied to clipboard

Challenge: CulturalBench is a set of 1,696 human-written and human-verified questions to assess LMs’ cultural knowledge covering 45 global regions including underrepresented ones like Bangladesh, Zimbabwe, and Peru.
Approach: They construct a set of 1,696 human-written and human-verified questions to assess LMs' cultural knowledge, covering 45 global regions including underrepresented ones like Bangladesh, Zimbabwe, and Peru.
Outcome: The proposed model outperforms other models across cultures, while underperforming on questions related to North Africa, South America and Middle East.
Learning to Generate Word- and Phrase-Embeddings for Efficient Phrase-Based Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: Neural machine translation (NMT) often fails in one-to-many translation, e.g., in the translation of multi-word expressions, compounds, and collocations.
Approach: They propose a phrase-based NMT model that generates embeddings of words or phrases.
Outcome: The proposed model performs on par with state-of-the-art phrase-based NMT.
Modular Pluralism: Pluralistic Alignment via Multi-LLM Collaboration (2024.emnlp-main)

Copied to clipboard

Challenge: Existing alignment paradigms for large language models learn an averaged human preference and struggle to model diverse preferences across cultures, demographics, and communities.
Approach: They propose a modular framework that "plugs" into a base LLM a pool of smaller but specialized community LMs where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional.
Outcome: The proposed framework “plugs into” a base LLM a pool of smaller but specialized community LMs, where models collaborate in distinct modes to support three modes of pluralism: Overton, steerable, and distributional.
ComPO: Community Preferences for Language Model Personalization (2025.naacl-long)

Copied to clipboard

Challenge: Current methods for training language models with human feedback rely on subjective preferences that are assumed to account for an "average" user . however, annotating preferences is inherently subjective and results in generic models that generate outputs not preferred by many user groups.
Approach: They propose a method to personalize preference optimization in LMs by contextualizing the probability distribution of model outputs with the preference provider.
Outcome: The proposed method improves performance by focusing on group-level preferences rather than individual feedback.
Locating Information Gaps and Narrative Inconsistencies Across Languages: A Case Study of LGBT People Portrayals on Wikipedia (2024.emnlp-main)

Copied to clipboard

Challenge: a recent study focuses on comparative text analyses to explain social phenomena and identify systematic biases.
Approach: They evaluate InfoGap method to locate information gaps and inconsistencies in articles at the fact level, across languages.
Outcome: The method identifies discrepancies in factual coverage across languages and biographical facts carrying negative connotations are more likely to be highlighted in Russian Wikipedia.
P3Sum: Preserving Author’s Perspective in News Summarization with Diffusion Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Existing summarization systems alter the political opinions and stances of news articles in more than 50% of summaries, misrepresenting the intent and perspectives of the authors.
Approach: They propose a model-based summarization approach controlled by political perspective classifiers that preserves the political stance of a generated summary.
Outcome: The proposed model outperforms state-of-the-art summarization systems and large language models by up to 13.7% in terms of success rate of stance preservation, with competitive performance on standard metrics of summarizing quality.
Challenges and Opportunities in Information Manipulation Detection: An Examination of Wartime Russian Media (2022.findings-emnlp)

Copied to clipboard

Challenge: Information manipulation campaigns rely on textbased news and social media content, and NLP can be a valuable tool in combating them.
Approach: They propose to use a dataset to examine the use of NLP in public opinion manipulation campaigns in the 2022 Russia-Ukraine war.
Outcome: The proposed dataset contains 38M+ posts from Russian media outlets on Twitter and VKontakte, as well as public activity and responses, immediately preceding and during the 2022 Russia-Ukraine war.
From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Models (2023.acl-long)

Copied to clipboard

Challenge: Hundreds of studies have highlighted ethical issues in NLP models .
Approach: They propose to measure media biases in LMs trained on diverse data sources . they focus on hate speech and misinformation detection .
Outcome: The proposed methods quantify the fairness of downstream NLP models trained on politically biased LMs.
Making VLMs More Robot-Friendly: Self-Critical Distillation of Low-Level Procedural Reasoning (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models (LLMs) are human-centric, but omit low-level, spatially grounded details needed for robotic execution.
Approach: They propose a lightweight framework for vision-language procedural planning that enables iteratively critique, revise and verify their own plans without external supervision or teacher models.
Outcome: a new framework outperforms weaker models 100X the size in vision-language procedural planning . the framework generates higher-quality, execution-ready plans that can be used at inference and fine-tuning .
Detecting Community Sensitive Norm Violations in Online Conversations (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing efforts to identify unacceptable behavior have focused on toxicity as the sole form of community norm violation.
Approach: They propose a dataset that focuses on a more complete spectrum of community norms and their violations in local conversational and global contexts.
Outcome: The proposed model improves the detection of community norm violations in local conversational and global contexts.
SPICA: Retrieving Scenarios for Pluralistic In-Context Alignment (2025.findings-acl)

Copied to clipboard

Challenge: In-context learning only considers similarity when drawing few-shot examples and not cross-group differences in values.
Approach: They propose a framework that accounts for group-level differences during in-context example retrieval by using scenario banks, group-informed retrieval metrics, and in-constraint alignment prompts.
Outcome: The proposed framework improves on an alignment task with groups seeing up to a +0.16 point improvement on a 5 point scale.
ValueScope: Unveiling Implicit Norms and Values via Return Potential Model of Social Interactions (2024.findings-emnlp)

Copied to clipboard

Challenge: VALUESCOPE is a framework that quantifies social norms and values within online communities.
Approach: They propose a framework that uses language models to quantify social norms and values within online communities.
Outcome: The proposed framework delineates differences in social norms and tracks evolution of norms in online communities and influence of significant external events like the U.S. presidential elections and the emergence of new sub-communities.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations