Papers by Soyeong Jeong
Improving Zero-shot Reader by Reducing Distractions from Irrelevant Documents in Open-Domain Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | 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. |
| Approach: | They propose to use a distraction-aware answer selection framework to mitigate the impact of irrelevant documents in the retrieved set and the overconfidence of the generated answers to enhance the performance of zero-shot readers. |
| Outcome: | The proposed approach handles distraction across diverse scenarios, enhancing the performance of zero-shot readers. |
Unified Multimodal Interleaved Document Representation for Retrieval (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods focus on textual content, ignoring the fact that documents can contain multiple modalities. |
| Approach: | They propose a method that holistically embeds documents interleaved with multiple modalities . they use vision-language models that combine text, images, and tables into a unified format . |
| Outcome: | The proposed method outperforms baselines on textual and multimodal queries. |
The RAG Paradox: A Black-Box Attack Exploiting Unintentional Vulnerabilities in Retrieval-Augmented Generation Systems (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to degrade retrieval-augmented generation systems rely on unrealistic assumptions in which external attackers have access to internal components such as the retriever. |
| Approach: | They propose a black-box attack based on the RAG paradox, a structural vulnerability that emerges from the system’s effort to enhance trust by revealing both the retrieved documents and their sources to users. |
| Outcome: | The proposed method significantly degrades system performance without internal access while generating natural-looking poisoned documents. |
Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative Decoding (2025.findings-naacl)
Copied to clipboard
Sukmin Cho, Sangjin Choi, Taeho Hwang, Jeongyeon Seo, Soyeong Jeong, Huije Lee, Hoyun Song, Jong C. Park, Youngjin Kwon
| Challenge: | Existing methods for drafting and verifying tokens require significant fine-tuning or have inconsistent performance across tasks. |
| Approach: | They propose a lossless drafting approach that organizes various token sources into multiple databases in a hierarchical framework based on temporal locality. |
| Outcome: | The proposed method outperforms existing database drafting methods on Spec-Bench using 7B and 13B parameters. |
UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-Augmented Generation (RAG) has shown substantial promise in improving factual accuracy by grounding model responses with external knowledge relevant to queries. |
| Approach: | They propose a framework to retrieve and integrate knowledge from heterogeneous sources with diverse modalities and granularities. |
| Outcome: | The proposed framework shows superiority over existing methods on 10 benchmarks of multiple modalities. |
VideoRAG: Retrieval-Augmented Generation over Video Corpus (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing approaches to generating models rely on text and images, but video content is a rich source of multimodal knowledge. |
| Approach: | They propose a framework that dynamically retrieves videos based on their relevance with queries . they use large video language models to represent video content for retrieval . |
| Outcome: | The proposed framework retrieves videos based on relevance with queries and integrates both visual and textual information. |
Database-Augmented Query Representation for Information Retrieval (2025.emnlp-main)
Copied to clipboard
| Challenge: | Information retrieval models that aim to search for documents relevant to a query have shown multiple successes, but the query from the user is oftentimes short, which challenges the retrievers to correctly fetch relevant documents. |
| Approach: | They propose a database-augmented Query representation framework which augments the query with various (query-related) metadata across multiple tables. |
| Outcome: | The proposed framework significantly improves overall retrieval performance over baselines. |
Typos that Broke the RAG’s Back: Genetic Attack on RAG Pipeline by Simulating Documents in the Wild via Low-level Perturbations (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing studies on the robustness of Large Language Models (LLMs) overlook the interconnected relationships between RAG components or the potential threats prevalent in real-world databases, such as minor textual errors. |
| Approach: | They propose a novel attack method that exploits vulnerabilities in RAG components and tests its robustness against noisy documents. |
| Outcome: | The proposed method devastates the performance of each component and their synergy, and significantly devases the performance. |
EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Current retrieval-augmented generation systems struggle when retrieval models fail to rank the most relevant documents . existing extractive methods reduce latency but rely on independent, non-adaptive sentence selection . |
| Approach: | They introduce an extractive context compression framework that enhances retrieval-augmented generation in question answering. |
| Outcome: | EXIT surpasses existing compression methods and uncompressed baselines in QA accuracy . the framework reduces inference time and token count while preserving contextual dependencies . |
Ask LLMs Directly, “What shapes your bias?”: Measuring Social Bias in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to evaluate social bias in large language models have limitations . et al., 1995: stereotypes shape social perceptions without objective basis . |
| Approach: | They propose a method to intuitively quantify social perceptions and suggest metrics to evaluate biases within LLMs. |
| Outcome: | The proposed metrics capture the multi-dimensional aspects of social bias, the paper shows . they show that the proposed metrics can be used to evaluate bias in large language models . |
Realistic Conversational Question Answering with Answer Selection based on Calibrated Confidence and Uncertainty Measurement (2023.eacl-main)
Copied to clipboard
| Challenge: | Existing work uses predicted answers instead of unavailable ground-truth answers as conversation history for inference. |
| Approach: | They propose to filter out inaccurate answers in the conversation history without making any architectural changes to the model. |
| Outcome: | The proposed models outperform baselines on two standard ConvQA datasets. |
When Thoughts Meet Facts: Reusable Reasoning for Long-Context LMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Recent Long-Context Language Models (LCLMs) do not capture how evidence should be connected . a new framework that integrates thought templates into LCLM frameworks is proving useful . |
| Approach: | They propose a framework that iteratively refines reusable reasoning patterns derived from prior problem solving to improve their templates. |
| Outcome: | The proposed framework outperforms baselines on knowledge-intensive multi-hop reasoning benchmarks and practical scenarios without retrieval. |
Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity (2024.naacl-long)
Copied to clipboard
| Challenge: | Recent Large Language Models (LLMs) generate factually incorrect answers based on their parametric memory. |
| Approach: | They propose a retrieval-augmented large language model that can dynamically select the most suitable strategy based on query complexity. |
| Outcome: | The proposed approach improves the performance of QA systems on open-domain QA datasets. |
CaMMT: Benchmarking Culturally Aware Multimodal Machine Translation (2025.findings-emnlp)
Copied to clipboard
Emilio Villa-Cueva, Sholpan Bolatzhanova, Diana Turmakhan, Kareem Elzeky, Henok Biadglign Ademtew, Alham Fikri Aji, Vladimir Araujo, Israel Abebe Azime, Jinheon Baek, Frederico Belcavello, Fermin Cristobal, Jan Christian Blaise Cruz, Mary Dabre, Raj Dabre, Toqeer Ehsan, Naome A Etori, Fauzan Farooqui, Jiahui Geng, Guido Ivetta, Thanmay Jayakumar, Soyeong Jeong, Zheng Wei Lim, Aishik Mandal, Sofía Martinelli, Mihail Minkov Mihaylov, Daniil Orel, Aniket Pramanick, Sukannya Purkayastha, Israfel Salazar, Haiyue Song, Tiago Timponi Torrent, Debela Desalegn Yadeta, Injy Hamed, Atnafu Lambebo Tonja, Thamar Solorio
| Challenge: | a human-curated benchmark of over 5,800 triples of images is used to evaluate multimodal translation systems. |
| Approach: | They introduce a human-curated benchmark of over 5,800 triples of images along with parallel captions in English and regional languages. |
| Outcome: | The results show that visual context improves translation quality in culturally-specific items . |
Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation (2022.acl-short)
Copied to clipboard
| Challenge: | Existing sparse retrieval models rely on term-based matching to retrieve relevant documents. |
| Approach: | They propose a framework which augments the representations of documents with interpolation and perturbation. |
| Outcome: | The proposed framework significantly outperforms baselines on the dense retrieval of both the labeled and unlabeled documents. |
Phrase Retrieval for Open Domain Conversational Question Answering with Conversational Dependency Modeling via Contrastive Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Open-Domain Conversational Question Answering (ODConvQA) aims to answer questions through a multi-turn conversation . however, such a pipeline approach makes the reader vulnerable to errors propagated from the retriever, which makes it slower since they are not runnable in parallel. |
| Approach: | They propose a method to directly predict answers with a phrase retrieval scheme for a sequence of words. |
| Outcome: | The proposed method outperforms the baselines on two ODConvQA datasets. |
Knowledge-Augmented Language Model Verification (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent Language Models (LMs) generate factually incorrect answers to queries . authors propose to augment LMs with knowledge retrieved from external source . |
| Approach: | They propose to augment LMs with knowledge retrieved from external sources . they validate the output and knowledge of the knowledge-augmented LM with a separate verifier . |
| Outcome: | The proposed model can generate factually incorrect answers on multiple questions . a verifier detects retrieval errors and can correct them by retrieving new knowledge or generating new text . |
Discrete Prompt Optimization via Constrained Generation for Zero-shot Re-ranker (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing studies suggest re-rankers by fine-tuning pre-trained language models . however, manual search for discrete prompts is expensive and sub-optimal in transferability . |
| Approach: | They propose a discrete prompt optimization method that guides the generated texts toward optimal prompts . they propose to use large-scale language models as a zero-shot re-ranker . |
| Outcome: | The proposed method improves the performance of the re-ranker against baselines and human prompts. |
Test-Time Self-Adaptive Small Language Models for Question Answering (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Recent instruction-finetuned large language models (LMs) have shown notable performances in various tasks, such as question-answering. |
| Approach: | They propose to use unlabeled test data to transfer smaller language models with limited knowledge. |
| Outcome: | The proposed strategy shows significant performance improvements on benchmark QA datasets with higher robustness across diverse prompts, enabling LMs to stay stable. |