Papers by Kee-Eung Kim

7 papers
End-to-End Neural Pipeline for Goal-Oriented Dialogue Systems using GPT-2 (2020.acl-main)

Copied to clipboard

Challenge: End-to-end dialogue systems with monolithic neural architecture are often trained with input-output utterances without taking into account the entire annotations available in the corpus.
Approach: They propose an end-to-end neural architecture for goal-oriented dialogue systems that addresses both challenges . they propose a modular architecture where modules are optimized individually .
Outcome: The proposed system achieved the top position in the human evaluation task . it is based on a neural architecture that can be integrated with external systems .
GDPO: Learning to Directly Align Language Models with Diversity Using GFlowNets (2024.emnlp-main)

Copied to clipboard

Challenge: Reinforcement learning with human feedback (RLHF) and its offline variant Direct Preference Optimization (DPO) are two of the most important methods for language model (LM) alignment.
Approach: They propose to use a diversity-seeking RL algorithm called GFlowNet-DPO in an offline preference alignment setting to optimize a model's behavior.
Outcome: Empirical results show that the proposed algorithm generates far more diverse responses than the baseline methods and is still relatively aligned with human values in dialog generation and summarization tasks.
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.
Hard Prompts Made Interpretable: Sparse Entropy Regularization for Prompt Tuning with RL (2024.acl-long)

Copied to clipboard

Challenge: Prompt tuning is an important technique for directing model behaviors and eliciting desired responses.
Approach: They propose to find optimal prompt tokens using soft Q-learning to optimize models for prompt tuning.
Outcome: The proposed method improves on baseline prompt tuning, and the results are more natural and interpretable.
PyOpenDial: A Python-based Domain-Independent Toolkit for Developing Spoken Dialogue Systems with Probabilistic Rules (D19-3)

Copied to clipboard

Challenge: a recent development of spoken dialogue systems has enabled deep learning to achieve state-of-the-art performance.
Approach: They propose a Python-based domain-independent, open-source toolkit for spoken dialogue systems.
Outcome: The proposed toolkit extends OpenDial's Java-based architecture and provides new functions for neural dialogue state tracking and action planning.
Bayesian Multi-Task Transfer Learning for Soft Prompt Tuning (2023.findings-emnlp)

Copied to clipboard

Challenge: Large-scale pre-trained language models have been fine-tuned for various NLP tasks . prompt tuning is a method that optimizes the output of the model to adapt to downstream tasks based on the posterior distribution of the source task.
Approach: They propose a Bayesian approach to prompt tuning that optimizes for adapting pre-trained language models to downstream tasks rather than fine-tuning full model parameters.
Outcome: The proposed approach outperforms the state-of-the-art methods on benchmark NLP tasks.
Learning to Embed Multi-Modal Contexts for Situated Conversational Agents (2022.findings-naacl)

Copied to clipboard

Challenge: Situated Interactive Multi-Modal Conversations 2.0 aims to create virtual shopping assistants that can accept complex multi-modal inputs.
Approach: They propose a joint learning approach that integrates visual inputs and performs all four subtasks at once for efficiency.
Outcome: The proposed approach won the 10th Dialog Systems Technology Challenge (DSTC10) . it incorporates visual inputs and performs all four subtasks at once for efficiency .

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