Papers by Seung-Hoon Na
PURE: Post-hoc Unlocking and REfinement for Discrete Diffusion Decoding (2026.findings-acl)
Copied to clipboard
| Challenge: | Masked diffusion language models (MDLMs) are limited by a monotonic unmasking policy, where committed tokens cannot be revised. |
| Approach: | They propose a training-free inference algorithm for two-phase decoding that unlocks unstable regions through deterministic window masking and stochastic leftward relaxation. |
| Outcome: | The proposed algorithm significantly improves accuracy on reasoning benchmarks on GSM8K. |
GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | GenPoE is a passage-level mixture of experts for enhancing knowledge of large language models. |
| Approach: | They propose a novel “generative” passage-level mixture of experts (MoEs) that takes in-context retrieved passages and generates their “expert” parameters. |
| Outcome: | The proposed system is based on a novel hypernetwork which takes in-context retrieved passages and generates their "expert'' parameters. |
LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory (2022.acl-short)
Copied to clipboard
| Challenge: | LM-BFF (CITATION) achieves significant few-shot performance by using auto-generated prompts and adding demonstrations similar to an input example. |
| Approach: | They propose to use auto-generated prompts and add demonstrations to LM-BFF to improve few-shot fine-tuning of language models with multiple soft demonstrations. |
| Outcome: | The proposed method improves few-shot fine-tuning on eight NLP tasks. |
MAFiD: Moving Average Equipped Fusion-in-Decoder for Question Answering over Tabular and Textual Data (2023.findings-eacl)
Copied to clipboard
| Challenge: | Experimental results show that Transformer-based questions have a "long" hybrid sequence over tabular and textual elements, causing long-range reasoning problems. |
| Approach: | They propose a moving average-equipped fusion-in-decoder to handle long-range reasoning problems . they use FiD and EMA to combine different levels of reasoning . |
| Outcome: | Experimental results show that the proposed model increases exact matching and F1 by 1.1 and 1.7 on the blind test set. |
SISER: Semantic-Infused Selective Graph Reasoning for Fact Verification (2022.coling-1)
Copied to clipboard
| Challenge: | Existing graph-based methods for fact verification use semantic graphs, which are based on evidence sentences. |
| Approach: | They propose to use semantic-level graph reasoning to inject its reasoning-enhanced representation into other graph-based and sequence-based reasoning methods. |
| Outcome: | The proposed method outperforms the previous graph-based methods and achieves state-of-the-art performance on a large-scale dataset for Fact Extraction and VERification (FEVER). |
EAIR: Entity-aware Inference-Time Knowledge Routing for Multi-Hop Knowledge Editing (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing in-context knowledge editing methods suffer from paraphrase sensitivity . Existing methods interfere with the model's original knowledge and can degrade its inherent capabilities. |
| Approach: | They propose a novel entity-aware inference-time knowledge routing method to address paraphrase sensitivity. |
| Outcome: | The proposed method achieves highest strict case accuracy in 11 of 12 settings, significantly reducing paraphrase sensitivity. |
COMEM: In-Context Retrieval-Augmented Mass-Editing Memory in Large Language Models (2024.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods for "knowledge editing" in large language models are inadequate . authors propose a method that can be used to update outdated information or correct false information . |
| Approach: | They propose a unified knowledge editing method called in-COntext retrieval-augmented Mass-Editing Memory . it incorporates retrieval augmented IKE, a novel extension of IKE designed for massive editing tasks . |
| Outcome: | The proposed method outperforms existing methods on the zsRE and CounterFact datasets. |
PRIME: Ultra-Low-Rank Principal–Residual Model Merging (2026.findings-acl)
Copied to clipboard
Seung-Ho Lee, Kyungsu Lee, Bazarvaani Zuchi, Jeongmin Ahn, Insuk Seo, Donghyeon Jeon, Inho Kang, Seung-Hoon Na
| Challenge: | Existing methods for model merging have been limited by task-specific performance and task-related tasks. |
| Approach: | They propose an ultra-low-rank principal-residual model merging framework that decomposes task vector merging into two stages. |
| Outcome: | Experiments on eight natural language processing tasks show that PRIME outperforms existing models while preserving the task-specific capabilities of the original models. |
DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | In-context knowledge editing has shown respectable abilities on knowledge editing in terms of generalization and specificity. |
| Approach: | They propose a novel extension of in-context knowledge editing (IKE) that allows for massive edits to be injected into large language models. |
| Outcome: | The proposed method shows state-of-the-art perfomrances and comparable performance with MIKE. |
RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion (2024.lrec-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated superior performance to that of small language models in information retrieval for various subtasks including dense retrieval, reranking, query expansion, and pseudo-document generation. |
| Approach: | They propose a retrieval-augmented model specialization that distills the capability of LLMs to generate the chain-of-thoughts (CoT) for query expansion into a RADCoT. |
| Outcome: | The proposed model can generate the chain-of-thoughts (CoT) for query expansion, reducing the burden of internalizing and retaining world knowledge in model parameters. |
ExplainMeetSum: A Dataset for Explainable Meeting Summarization Aligned with Human Intent (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for meeting summarization use extract-thengenerate method to select "salient" contents . extract-thangenerates method typically selects "selected" content in a distantly supervised manner . |
| Approach: | They propose a novel extractor-guided method to generate a summary from evidence sentences that "explain" a meeting summary. |
| Outcome: | The proposed method outperforms existing methods with gains of up to 3.13 in the ROUGE-1 score. |
Frustratingly Easy System Combination for Grammatical Error Correction (2022.naacl-main)
Copied to clipboard
| Challenge: | Using a simple logistic regression algorithm, we combine GEC models for binary classification. |
| Approach: | They propose a logistic regression algorithm that can combine GEC models with binary classification. |
| Outcome: | The proposed method outperforms the state-of-the-art by 4.2 points on the CoNLL-2014 and 7.2 points on BEA-2019 test sets. |
DiffusionRet: Diffusion-Enhanced Generative Retriever using Constrained Decoding (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Generative retrieval methods have suffered from the lack of the intermediate reasoning step . generative retrieval uses sequence-to-sequence diffusion models to map a query to relevant docids . |
| Approach: | They propose a novel method that uses query as an intermediate step before retrieval . they propose to use sequence-to-sequence diffusion models to map a query to relevant docids . |
| Outcome: | Experiments show that proposed method outperforms existing methods on MARCO and Natural Questions datasets. |
SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing research has demonstrated strong performance in single-instance or few-instantial sequential editing and one-time massive editing scenarios, but the batched sequential editing paradigm remains a significant challenge. |
| Approach: | They propose a framework for batched sequential knowledge editing that leverages **SeqMMR** and a model router to merge parameters from current batch-edited models with those of their predecessors. |
| Outcome: | The proposed framework iteratively merges parameters from current batch-edited models with those of their predecessors, ensuring that newly emerging knowledge is integrated while mitigating the forgetting of previously edited knowledge. |
SARCAT: Generative Span-Act Guided Response Generation using Copy-enhanced Target Augmentation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches for document-grounded dialogue systems are based on retrieve-and-generate frameworks. |
| Approach: | They propose a novel extension to improve document grounded response generation by incorporating a copy mechanism into a augmentation. |
| Outcome: | The proposed extension improves the document-grounded response generation performance even with the base reader. |