35 citations · 81 across the 27 of their papers we have counts for
27 papers · 1 filter
A Unified Mechanistic Analysis of Knowledge- and Safety-Based Refusals
Yuri Son, Seunghee Kim, Hyuhng Joon Kim +1
Large language models (LLMs) are increasingly trained to decline queries that fall outside their knowledge (knowledge-based refusal, KR) or violate safety policies (safety-based re…
UniKnow: A Unified Framework for Reliable Language Model Behavior across Parametric and External Knowledge
Youna Kim, Hyuhng Joon Kim, Minjoon Choi +4
Language models often benefit from external knowledge beyond parametric knowledge. While this combination enhances performance, achieving reliable knowledge utilization remains cha…
When to Speak, When to Abstain: Contrastive Decoding with Abstention
Hyuhng Joon Kim, Youna Kim, Sang-goo Lee +1
Large Language Models (LLMs) demonstrate exceptional performance across diverse tasks by leveraging pre-trained (i.e., parametric) and external (i.e., contextual) knowledge. While…
Adaptive Contrastive Decoding in Retrieval-Augmented Generation for Handling Noisy Contexts
Youna Kim, Hyuhng Joon Kim, Cheonbok Park +6
When using large language models (LLMs) in knowledge-intensive tasks, such as open-domain question answering, external context can bridge the gap between external knowledge and the…
Investigating the Influence of Prompt-Specific Shortcuts in AI Generated Text Detection
Choonghyun Park, Hyuhng Joon Kim, Junyeob Kim +6
AI Generated Text (AIGT) detectors are developed with texts from humans and LLMs of common tasks. Despite the diversity of plausible prompt choices, these datasets are generally co…
Aligning Language Models to Explicitly Handle Ambiguity
Hyuhng Joon Kim, Youna Kim, Cheonbok Park +5
In interactions between users and language model agents, user utterances frequently exhibit ellipsis (omission of words or phrases) or imprecision (lack of exactness) to prioritize…
Analysis of Multi-Source Language Training in Cross-Lingual Transfer
Seong Hoon Lim, Taejun Yun, Jinhyeon Kim +2
The successful adaptation of multilingual language models (LMs) to a specific language-task pair critically depends on the availability of data tailored for that condition. While c…
X-SNS: Cross-Lingual Transfer Prediction through Sub-Network Similarity
Taejun Yun, Jinhyeon Kim, Deokyeong Kang +3
Cross-lingual transfer (XLT) is an emergent ability of multilingual language models that preserves their performance on a task to a significant extent when evaluated in languages t…
Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP
Hyuhng Joon Kim, Hyunsoo Cho, Sang-Woo Lee +5
When deploying machine learning systems to the wild, it is highly desirable for them to effectively leverage prior knowledge to the unfamiliar domain while also firing alarms to an…
Prompt-Augmented Linear Probing: Scaling beyond the Limit of Few-shot In-Context Learners
Hyunsoo Cho, Hyuhng Joon Kim, Junyeob Kim +4
Through in-context learning (ICL), large-scale language models are effective few-shot learners without additional model fine-tuning. However, the ICL performance does not scale wel…
Revisiting the Practical Effectiveness of Constituency Parse Extraction from Pre-trained Language Models
Taeuk Kim
Constituency Parse Extraction from Pre-trained Language Models (CPE-PLM) is a recent paradigm that attempts to induce constituency parse trees relying only on the internal knowledg…
Enhancing Out-of-Distribution Detection in Natural Language Understanding via Implicit Layer Ensemble
Hyunsoo Cho, Choonghyun Park, Jaewook Kang +3
Out-of-distribution (OOD) detection aims to discern outliers from the intended data distribution, which is crucial to maintaining high reliability and a good user experience. Most…
Self-Generated In-Context Learning: Leveraging Auto-regressive Language Models as a Demonstration Generator
Hyuhng Joon Kim, Hyunsoo Cho, Junyeob Kim +3
Large-scale pre-trained language models (PLMs) are well-known for being capable of solving a task simply by conditioning a few input-label pairs dubbed demonstrations on a prompt w…
HYU at SemEval-2022 Task 2: Effective Idiomaticity Detection with Consideration at Different Levels of Contextualization
Youngju Joung, Taeuk Kim
We propose a unified framework that enables us to consider various aspects of contextualization at different levels to better identify the idiomaticity of multi-word expressions. T…
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations
Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim +5
Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive. Intuitively, ground-t…
Self-Guided Contrastive Learning for BERT Sentence Representations
Taeuk Kim, Kang Min Yoo, Sang-goo Lee
Although BERT and its variants have reshaped the NLP landscape, it still remains unclear how best to derive sentence embeddings from such pre-trained Transformers. In this work, we…
Heads-up! Unsupervised Constituency Parsing via Self-Attention Heads
Bowen Li, Taeuk Kim, Reinald Kim Amplayo +1
Transformer-based pre-trained language models (PLMs) have dramatically improved the state of the art in NLP across many tasks. This has led to substantial interest in analyzing the…
IDS at SemEval-2020 Task 10: Does Pre-trained Language Model Know What to Emphasize?
Jaeyoul Shin, Taeuk Kim, Sang-goo Lee
We propose a novel method that enables us to determine words that deserve to be emphasized from written text in visual media, relying only on the information from the self-attentio…
Multilingual Chart-based Constituency Parse Extraction from Pre-trained Language Models
Taeuk Kim, Bowen Li, Sang-goo Lee
As it has been unveiled that pre-trained language models (PLMs) are to some extent capable of recognizing syntactic concepts in natural language, much effort has been made to devel…
Are Pre-trained Language Models Aware of Phrases? Simple but Strong Baselines for Grammar Induction
Taeuk Kim, Jihun Choi, Daniel Edmiston +1
With the recent success and popularity of pre-trained language models (LMs) in natural language processing, there has been a rise in efforts to understand their inner workings. In…
Summary Level Training of Sentence Rewriting for Abstractive Summarization
Sanghwan Bae, Taeuk Kim, Jihoon Kim +1
As an attempt to combine extractive and abstractive summarization, Sentence Rewriting models adopt the strategy of extracting salient sentences from a document first and then parap…
Don't Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja
Kang Min Yoo, Taeuk Kim, Sang-goo Lee
We propose a simple yet effective approach for improving Korean word representations using additional linguistic annotation (i.e. Hanja). We employ cross-lingual transfer learning…
A Cross-Sentence Latent Variable Model for Semi-Supervised Text Sequence Matching
Jihun Choi, Taeuk Kim, Sang-goo Lee
We present a latent variable model for predicting the relationship between a pair of text sequences. Unlike previous auto-encoding--based approaches that consider each sequence sep…
Dynamic Compositionality in Recursive Neural Networks with Structure-aware Tag Representations
Taeuk Kim, Jihun Choi, Daniel Edmiston +2
Most existing recursive neural network (RvNN) architectures utilize only the structure of parse trees, ignoring syntactic tags which are provided as by-products of parsing. We pres…