Papers by Seongmin Lee

12 papers
Enhancing Time Awareness in Generative Recommendation (2025.findings-emnlp)

Copied to clipboard

Challenge: Existing models focus on sequential order of items and neglect to handle temporal dynamics . existing models neglect to capture hidden user preferences via various temporal signals .
Approach: They propose a model that generates recommendations into a text-to-text generation task . they introduce Time-aware Prompting and Trend-awful Inference .
Outcome: The proposed model outperforms state-of-the-art models with gains of 15.4% and 14.3% . it is based on time-aware Prompting and Trend-awful Inference .
RT-VQ2A2: Real Time Vector Quantized Question Answering with ASR (2024.lrec-main)

Copied to clipboard

Challenge: Existing frameworks for QA with large language models are difficult to implement due to noise, limited context length and latency.
Approach: They propose a model-agnostic framework to address problems in QA with large language models.
Outcome: The proposed framework reduces noise in the ASR output and the limited context length of LLMs and improves performance on the widely used Spoken-SQuAD dataset.
Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings (2022.acl-long)

Copied to clipboard

Challenge: Recent studies have determined that the learned token embeddings of large-scale neural language models are degenerated to be anisotropic with a narrow-cone shape.
Approach: They propose a method to degenerate the learning gradient for rare token embeddings by gating the specific part of the gradient for all tokens during training stage.
Outcome: The proposed method improves the performance of the models but lacks the training dynamics needed to solve the representation degeneration problem.
LIME: Weakly-Supervised Text Classification without Seeds (2022.coling-1)

Copied to clipboard

Challenge: Existing approaches to weakly-supervised text classification use only label names as sources of supervision.
Approach: They propose a framework for weakly-supervised text classification that replaces seed-word generation with entailment-based pseudo-classification.
Outcome: The proposed framework outperforms baselines and state-of-the-art in 4 benchmarks.
Interpretation Meets Safety: A Survey on Interpretation Methods and Tools for Improving LLM Safety (2025.emnlp-main)

Copied to clipboard

Challenge: Existing surveys focus on interpretation or safety, but safety and understanding are core motivations for interpretation research.
Approach: They propose a framework that connects interpretation methods, enhancements they inform, and tools that operationalize them.
Outcome: The proposed framework summarizes nearly 70 studies at their intersections and concludes with open challenges and future directions.
Goal-Conditioned DPO: Prioritizing Safety in Misaligned Instructions (2025.naacl-long)

Copied to clipboard

Challenge: Existing defense methods focus on aligning the model’s output towards less harmful responses through post-processing or input perturbation.
Approach: They propose a goal-conditioned direct preference optimization technique which is trained to prioritize the system prompt over the user prompt through goal-conditioning and reduces the average Attack Success Rate (ASR) on a wide variety of jailbreak attacks.
Outcome: The proposed approach reduces the average Attack Success Rate (ASR) on a wide variety of jailbreak attacks while maintaining general performance.
Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment (2024.acl-long)

Copied to clipboard

Challenge: Quantization-aware direct preference optimization (QDPO) improves conversational abilities of quantized LLMs . token-flipping is a critical factor for degraded text generation quality .
Approach: They propose a method that aligns quantized LLMs with their full-precision counterparts, improving conversational abilities.
Outcome: The proposed method outperforms established fine-tuning techniques on two instruction-tuned LLMs in various languages and models, setting a new benchmark for conversational chatbot development.
KNU-HYUNDAI’s NMT system for Scientific Paper and Patent Tasks onWAT 2019 (D19-52)

Copied to clipboard

Challenge: We submitted our transformer-based neural machine translation system to the translation tasks of the 6th workshop on Asian Translation (WAT 2019).
Approach: They propose a transformer-based neural machine translation system for Chinese-Japanese, English-Japanese, and Korean->Japanoise translation tasks.
Outcome: The proposed system performed well on the two translation tasks and was ranked first in terms of the BLEU scores in all the JPC2 subtasks.
Let LLM Tutors Ask First: Proactive LLM-Based Tutoring at Scale in a 1,500-Student Online Classroom (2026.acl-industry)

Copied to clipboard

Challenge: Large-scale introductory CS courses struggle to provide personalized support and encourage active participation.
Approach: They propose to use predictive query management to generate student questions and answers ahead of lectures and to engage in interactive conversations with a tutoring model.
Outcome: The proposed learning assistant generates student questions and answers ahead of lectures and interacts with students via the same interface.
Cross-task Knowledge Transfer for Extremely Weakly Supervised Text Classification (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods for text classification with extremely weak supervision impose stricter supervision constraints than those under regular weak supervision.
Approach: They propose a framework that creates weak labels by leveraging recent developments in zero-shot text classification.
Outcome: The proposed framework outperforms existing methods on weak labels generated by weakly supervise classification.
Non-Essential Is NEcessary: Order-agnostic Multi-hop Question Generation (2024.lrec-main)

Copied to clipboard

Challenge: Existing multi-hop question generation methods treat answer-irrelevant documents as non-essential and remove them as impurities, which can lead to a decrease in model performance.
Approach: They propose a task which leverages non-essential data in the training phase to create a robust model and extract the consistent embeddings in real-world inference environments.
Outcome: The proposed model can perform ranker and generator without external modules and achieves state-of-the-art on a hotpotQA dataset.
Empowering Retrieval-based Conversational Recommendation with Contrasting User Preferences (2025.naacl-long)

Copied to clipboard

Challenge: Existing CRSs assume positive and negative user preferences, but assume that the entities in the dialogue history are positive.
Approach: They propose a conversational recommender model that captures user sentiments and uses the reasoning capacity of the LLMs to extract user's hidden preferences.
Outcome: The proposed model outperforms existing methods in three benchmark datasets, improving up to 99.72% in Recall@10.

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