Papers by Sang-Woo Lee

18 papers
Plug-and-Play Adaptation for Continuously-updated QA (2022.findings-acl)

Copied to clipboard

Challenge: Existing tasks to assess LMs’ efficacy as KBs do not adequately consider multiple large-scale updates.
Approach: They propose a task where multiple large-scale updates are made to language models and plug-in modules are used to handle the updates.
Outcome: The proposed method outperforms existing methods on zsRE QA and NQ datasets and is 4x more effective in terms of updates/forgets ratio compared to a fine-tuning baseline.
Continuous Decomposition of Granularity for Neural Paraphrase Generation (2022.coling-1)

Copied to clipboard

Challenge: Prior work has shown that decomposing sentences at different levels of granularity has improved paragraph generation.
Approach: They propose a model for continuous decomposing granularity for neural paraphrase generation that incorporates granules into attention.
Outcome: The proposed model outperforms baseline models on Quora question pairs and Twitter URLs on two benchmarks.
Ground-Truth Labels Matter: A Deeper Look into Input-Label Demonstrations (2022.emnlp-main)

Copied to clipboard

Challenge: Intuitively, ground-truth labels should have as much impact in in-context learning as supervised learning, but the impact of the quality of demonstrations remains elusive.
Approach: They propose to measure input-label correspondence and ground-truth label effect ratio . they propose to use verbosity of prompt templates and language model size as controlling factors .
Outcome: The proposed metrics show that ground-truth labels have less impact than previously thought . the authors identify key components as controlling factors to achieve noise-resilient ICL .
Query-Efficient Black-Box Red Teaming via Bayesian Optimization (2023.acl-long)

Copied to clipboard

Challenge: Existing methods for generating test cases and querying fail to be query-efficient . generative models can be used for open-domain dialogue, prompt continuation, text-to-image generation .
Approach: They propose a query-efficient method that iteratively finds diverse positive test cases leading to model failures by utilizing user input and past evaluations.
Outcome: The proposed method finds a significantly larger number of diverse positive test cases under limited query budget than baseline methods.
Efficient Dialogue State Tracking by Selectively Overwriting Memory (2020.acl-main)

Copied to clipboard

Challenge: Recent work in dialogue state tracking (DST) is inefficient in that it predicts dialogue state at every turn from scratch.
Approach: They propose a method that selectively overwrites memory for dialogue state tracking by predicting dialogue state on each memory slot and overwriting it with new values.
Outcome: The proposed model achieves state-of-the-art joint goal accuracy with 51.72% in MultiWOZ 2.0 and 53.01% in MultiWoz 2.1 in an open vocabulary-based DST setting.
How Well Can Reasoning Models Identify and Recover from Unhelpful Thoughts? (2025.findings-emnlp)

Copied to clipboard

Challenge: Recent reasoning models show the ability to reflect, backtrack, and self-validate their reasoning .
Approach: They investigate how well models identify and recover from unhelpful thoughts . they show that models are effective at identifying most unhelpfully thoughts - but struggle to recover from the same thoughts when they are injected into their thinking process .
Outcome: The proposed model can identify unhelpful thoughts but struggle to recover from them . larger models struggle more than smaller models to recover short irrelevant thoughts .
Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning (2023.acl-long)

Copied to clipboard

Challenge: Recent studies have proposed unified user modeling frameworks that leverage user behavior data from various applications.
Approach: They propose to use user behavior sequences as plain text to represent rich information in any domain or system without losing generality.
Outcome: The proposed frameworks achieve excellent results on diverse recommendation tasks and can be used on unseen domains and services.
On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model (2022.naacl-main)

Copied to clipboard

Challenge: Recent studies on large-scale in-context language models have reported successful in-const zero- and few-shot learning ability.
Approach: They investigate the effects of the pretraining corpus on in-context learning in a Korean-centric model.
Outcome: The study shows that pretraining corpus size does not determine in-context learning ability . the findings suggest that in-constext learning is not always competitive .
Asking Clarification Questions to Handle Ambiguity in Open-Domain QA (2023.findings-emnlp)

Copied to clipboard

Challenge: Ambiguous questions persist in open-domain question answering because formulating a precise question with a unique answer is often challenging.
Approach: They propose to ask a clarification question where the user’s response will help identify the interpretation that best aligns with the user's intention.
Outcome: The proposed approach achieves F1 of 61.3, 25.1, and 40.5 on the three tasks, demonstrating the need for further improvements while providing competitive baselines for future work.
NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation (2021.acl-long)

Copied to clipboard

Challenge: NeuralWOZ generates dialogues from user’s goal instructions and system’s API call results.
Approach: They propose a framework that uses model-based dialogue simulation to generate dialogues from user’s goal instructions and system’s API call results.
Outcome: The proposed framework achieves 4.4% point joint goal accuracy on average across domains and 5.7% point of zero-shot coverage against the MultiWOZ 2.1 dataset.
Weakly Supervised Pre-Training for Multi-Hop Retriever (2021.findings-acl)

Copied to clipboard

Challenge: Existing methods for weakly supervised multi-hop pretraining require costly human annotation.
Approach: They propose a method for weakly supervised multi-hop retriever pretraining without human efforts by generating vector representations of complex questions and subquestion as weak supervision for pre-training.
Outcome: The proposed method is effective and robust on limited data and computational resources.
GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation (2021.findings-emnlp)

Copied to clipboard

Challenge: Recent studies report that prompt-based direct classification eliminates the need for fine-tuning but lacks data and inference scalability.
Approach: They propose a data augmentation technique that leverages large-scale language models to generate real text samples from a mixture of real samples.
Outcome: The proposed method outperforms existing methods on diverse classification tasks.
Keep Me Updated! Memory Management in Long-term Conversations (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing studies do not deal with cases where memorized information is outdated, which may cause confusion in later conversations.
Approach: They propose a task where bots keep track of and bring up the latest information about users while conversing through multiple sessions.
Outcome: The proposed method outperforms baselines that leave the stored memory unchanged in terms of engagingness and humanness, and a larger performance gap in the later sessions.
Two-Step Question Retrieval for Open-Domain QA (2022.findings-acl)

Copied to clipboard

Challenge: Existing question retrieval models have shown a significant increase in inference speed but at the cost of lower QA performance compared to the retriever-reader pipeline.
Approach: They propose a two-step question retrieval model with distant supervision to improve inference speed.
Outcome: The proposed model significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.
Universal Domain Adaptation for Robust Handling of Distributional Shifts in NLP (2023.findings-emnlp)

Copied to clipboard

Challenge: Despite advances in computer vision, its application on language input still needs to be explored despite its feasibility.
Approach: They propose a universal domain adaptation (uniDA) benchmark for natural language that offers thorough viewpoints of the model’s generalizability and robustness.
Outcome: The proposed model can handle spoken language in the real world while also detecting unprocessable inputs from the target domain.
Attribute Injection for Pretrained Language Models: A New Benchmark and an Efficient Method (2022.coling-1)

Copied to clipboard

Challenge: Recent models rely on pretrained language models that use metadata as inputs . however, these methods are either nontrivial or cost-ineffective .
Approach: They propose a benchmark for evaluating attribute injection models using eight datasets . they extend adapters to include attributes independently of or jointly with the text .
Outcome: The proposed method outperforms previous methods and achieves state-of-the-art performance on all datasets.
Building a Role Specified Open-Domain Dialogue System Leveraging Large-Scale Language Models (2022.naacl-main)

Copied to clipboard

Challenge: Recent large-scale language models have produced human-like responses in open-domain dialogue systems.
Approach: They propose a framework for imposing roles on open-domain dialogue systems . they use few-shot learning to build a Korean dialogue dataset from scratch .
Outcome: The proposed framework meets role specifications while maintaining conversational abilities.

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