AIConfPaper
← Search

Soyeong Jeong

16 accepted papers

2025

CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation

Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji +29
EMNLP 2025

Translating cultural content poses challenges for machine translation systems due to the differences in conceptualizations between cultures, where language alone may fail to convey sufficient context to capture region-specific meanings. In this work, we investigate whether images can act as cultural

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Database-Augmented Query Representation for Information Retrieval

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong C. Park
EMNLP 2025

Information retrieval models that aim to search for documents relevant to a query have shown multiple successes, which have been applied to diverse tasks. Yet, the query from the user is oftentimes short, which challenges the retrievers to correctly fetch relevant documents. To tackle this, previous

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation

Taeho Hwang, Sukmin Cho, Soyeong Jeong, Hoyun Song, SeungYoon Han, Jong C. Park
ACL 2025finding

We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA). Current RAG systems often struggle when retrieval models fail to rank the most relevant documents, leading to the inc…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding

Sukmin Cho, Sangjin Choi, Taeho Hwang, Jeongyeon Seo, Soyeong Jeong, Huije Lee +3
NAACL 2025findings

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for improving inference speed by drafting and verifying tokens, ther…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems

Chanwoo Choi, Jinsoo Kim, Sukmin Cho, Soyeong Jeong, Buru Chang
EMNLP 2025

With the growing adoption of retrieval-augmented generation (RAG) systems, various attack methods have been proposed to degrade their performance. However, most existing approaches rely on unrealistic assumptions in which external attackers have access to internal components such as the retriever. T

Cited by 0Source ↗PDF ↗Scholar ↗
2025

VideoRAG: Retrieval-Augmented Generation over Video Corpus

Soyeong Jeong, Kangsan Kim, Jinheon Baek, Sung Ju Hwang
ACL 2025finding

Retrieval-Augmented Generation (RAG) is a powerful strategy for improving the factual accuracy of models by retrieving external knowledge relevant to queries and incorporating it into the generation process. However, existing approaches primarily focus on text, with some recent advancements consider…

Cited by 61Source ↗PDF ↗code ↗Scholar ↗
2024

Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong Park
NAACL 2024long

Retrieval-Augmented Large Language Models (LLMs), which incorporate the non-parametric knowledge from external knowledge bases into LLMs, have emerged as a promising approach to enhancing response accuracy in several tasks, such as Question-Answering (QA). However, even though there are various appr…

Cited by 162Source ↗PDF ↗code ↗Scholar ↗
2024

Ask LLMs Directly, “What shapes your bias?”: Measuring Social Bias in Large Language Models

Jisu Shin, Hoyun Song, Huije Lee, Soyeong Jeong, Jong Park
ACL 2024findings

Social bias is shaped by the accumulation of social perceptions towards targets across various demographic identities. To fully understand such social bias in large language models (LLMs), it is essential to consider the composite of social perceptions from diverse perspectives among identities. Pre…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark

David Orlando Romero Mogrovejo, Chenyang Lyu, Haryo Akbarianto Wibowo, Santiago Góngora, Aishik Mandal, Sukannya Purkayastha +70
NeurIPS 2024oral

Visual Question Answering~(VQA) is an important task in multimodal AI, which requires models to understand and reason on knowledge present in visual and textual data. However, most of the current VQA datasets and models are primarily focused on English and a few major world languages, with images th…

Cited by 34Source ↗PDF ↗Scholar ↗
2024

Typos that Broke the RAG’s Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations

Sukmin Cho, Soyeong Jeong, Jeongyeon Seo, Taeho Hwang, Jong C. Park
EMNLP 2024finding

The robustness of recent Large Language Models (LLMs) has become increasingly crucial as their applicability expands across various domains and real-world applications. Retrieval-Augmented Generation (RAG) is a promising solution for addressing the limitations of LLMs, yet existing studies on the ro…

Cited by 25Source ↗PDF ↗code ↗Scholar ↗
2023

Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker

Sukmin Cho, Soyeong Jeong, Jeong yeon Seo, Jong Park
ACL 2023findings

Re-rankers, which order retrieved documents with respect to the relevance score on the given query, have gained attention for the information retrieval (IR) task. Rather than fine-tuning the pre-trained language model (PLM), the large-scale language model (LLM) is utilized as a zero-shot re-ranker w…

Cited by 21Source ↗PDF ↗code ↗Scholar ↗
2023

Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering

Sukmin Cho, Jeongyeon Seo, Soyeong Jeong, Jong C. Park
EMNLP 2023short findings

Large language models (LLMs) enable zero-shot approaches in open-domain question answering (ODQA), yet with limited advancements as the reader is compared to the retriever. This study aims at the feasibility of a zero-shot reader that addresses the challenges of computational cost and the need for l…

Cited by 0Source ↗Scholar ↗
2023

Knowledge-Augmented Language Model Verification

Jinheon Baek, Soyeong Jeong, Minki Kang, Jong C. Park, Sung Ju Hwang
EMNLP 2023long main

Recent Language Models (LMs) have shown impressive capabilities in generating texts with the knowledge internalized in parameters. Yet, LMs often generate the factually incorrect responses to the given queries, since their knowledge may be inaccurate, incomplete, and outdated. To address this proble…

Cited by 0Source ↗code ↗Scholar ↗
2023

Phrase Retrieval for Open Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning

Soyeong Jeong, Jinheon Baek, Sung Ju Hwang, Jong Park
ACL 2023findings

Open-Domain Conversational Question Answering (ODConvQA) aims at answering questions through a multi-turn conversation based on a retriever-reader pipeline, which retrieves passages and then predicts answers with them. However, such a pipeline approach not only makes the reader vulnerable to the err…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2023

Test-Time Self-Adaptive Small Language Models for Question Answering

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong C. Park
EMNLP 2023short findings

Recent instruction-finetuned large language models (LMs) have achieved notable performances in various tasks, such as question-answering (QA). However, despite their ability to memorize a vast amount of general knowledge across diverse tasks, they might be suboptimal on specific tasks due to their l…

Cited by 0Source ↗code ↗Scholar ↗
2022

Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation

Soyeong Jeong, Jinheon Baek, Sukmin Cho, Sung Ju Hwang, Jong Park
ACL 2022short

Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a vast amount of labeled training data for notable performance, whereas it is ofte…

Cited by 10Source ↗PDF ↗code ↗Scholar ↗