7.5k citations · 7.7k across the 32 of their papers we have counts for
32 papers
RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation
Byeongguk Jeon, Seonghyeon Ye, JaeHyeok Doo +4
Video world models are emerging as a scalable alternative for evaluating generalist robot policies, bypassing the physical constraints and engineering burdens of real-world deploym…
HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation
Jaehwi Song, Suchae Jeong, Byeongguk Jeon +4
Large-scale demonstration datasets have been central to recent progress in general-purpose robot policies. However, existing datasets are collected in human-absent settings, and po…
Generative Prompt Internalization
Haebin Shin, Lei Ji, Yeyun Gong +3
Prompts used in recent large language model based applications are often fixed and lengthy, leading to significant computational overhead. To address this challenge, we propose Gen…
HyperCLOVA X Technical Report
Kang Min Yoo, Jaegeun Han, Sookyo In +393
We introduce HyperCLOVA X, a family of large language models (LLMs) tailored to the Korean language and culture, along with competitive capabilities in English, math, and coding. H…
Ask Optimal Questions: Aligning Large Language Models with Retriever's Preference in Conversation
Chanwoong Yoon, Gangwoo Kim, Byeongguk Jeon +3
Conversational search, unlike single-turn retrieval tasks, requires understanding the current question within a dialogue context. The common approach of rewrite-then-retrieve aims…
KMMLU: Measuring Massive Multitask Language Understanding in Korean
Guijin Son, Hanwool Lee, Sungdong Kim +6
We propose KMMLU, a new Korean benchmark with 35,030 expert-level multiple-choice questions across 45 subjects ranging from humanities to STEM. While prior Korean benchmarks are tr…
Aligning Large Language Models by On-Policy Self-Judgment
Sangkyu Lee, Sungdong Kim, Ashkan Yousefpour +3
Existing approaches for aligning large language models with human preferences face a trade-off that requires a separate reward model (RM) for on-policy learning. In this paper, we…
Rethinking the Role of Proxy Rewards in Language Model Alignment
Sungdong Kim, Minjoon Seo
Learning from human feedback via proxy reward modeling has been studied to align Large Language Models (LLMs) with human values. However, achieving reliable training through that p…
LangBridge: Multilingual Reasoning Without Multilingual Supervision
Dongkeun Yoon, Joel Jang, Sungdong Kim +3
We introduce LangBridge, a zero-shot approach to adapt language models for multilingual reasoning tasks without multilingual supervision. LangBridge operates by bridging two models…
Tree of Clarifications: Answering Ambiguous Questions with Retrieval-Augmented Large Language Models
Gangwoo Kim, Sungdong Kim, Byeongguk Jeon +2
Questions in open-domain question answering are often ambiguous, allowing multiple interpretations. One approach to handling them is to identify all possible interpretations of the…
Prometheus: Inducing Fine-grained Evaluation Capability in Language Models
Seungone Kim, Jamin Shin, Yejin Cho +8
Recently, using a powerful proprietary Large Language Model (LLM) (e.g., GPT-4) as an evaluator for long-form responses has become the de facto standard. However, for practitioners…
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
Seonghyeon Ye, Doyoung Kim, Sungdong Kim +6
Evaluation of Large Language Models (LLMs) is challenging because instruction-following necessitates alignment with human values and the required set of skills varies depending on…
Gradient Ascent Post-training Enhances Language Model Generalization
Dongkeun Yoon, Joel Jang, Sungdong Kim +1
In this work, we empirically show that updating pretrained LMs (350M, 1.3B, 2.7B) with just a few steps of Gradient Ascent Post-training (GAP) on random, unlabeled text corpora enh…
Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization
Jeonghoon Kim, Jung Hyun Lee, Sungdong Kim +4
Large language models (LLMs) face the challenges in fine-tuning and deployment due to their high memory demands and computational costs. While parameter-efficient fine-tuning (PEFT…
Revealing User Familiarity Bias in Task-Oriented Dialogue via Interactive Evaluation
Takyoung Kim, Jamin Shin, Young-Ho Kim +2
Most task-oriented dialogue (TOD) benchmarks assume users that know exactly how to use the system by constraining the user behaviors within the system's capabilities via strict use…
Aligning Large Language Models through Synthetic Feedback
Sungdong Kim, Sanghwan Bae, Jamin Shin +4
Aligning large language models (LLMs) to human values has become increasingly important as it enables sophisticated steering of LLMs. However, it requires significant human demonst…
Semi-Parametric Video-Grounded Text Generation
Sungdong Kim, Jin-Hwa Kim, Jiyoung Lee +1
Efficient video-language modeling should consider the computational cost because of a large, sometimes intractable, number of video frames. Parametric approaches such as the attent…
Leveraging Large Language Models to Power Chatbots for Collecting User Self-Reported Data
Jing Wei, Sungdong Kim, Hyunhoon Jung +1
Large language models (LLMs) provide a new way to build chatbots by accepting natural language prompts. Yet, it is unclear how to design prompts to power chatbots to carry on natur…
Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?
Sang-Woo Lee, Sungdong Kim, Donghyeon Ko +9
Task-oriented dialogue (TOD) systems are mainly based on the slot-filling-based TOD (SF-TOD) framework, in which dialogues are broken down into smaller, controllable units (i.e., s…
Keep Me Updated! Memory Management in Long-term Conversations
Sanghwan Bae, Donghyun Kwak, Soyoung Kang +7
Remembering important information from the past and continuing to talk about it in the present are crucial in long-term conversations. However, previous literature does not deal wi…
Leveraging Pre-Trained Language Models to Streamline Natural Language Interaction for Self-Tracking
Young-Ho Kim, Sungdong Kim, Minsuk Chang +1
Current natural language interaction for self-tracking tools largely depends on bespoke implementation optimized for a specific tracking theme and data format, which is neither gen…
On the Effect of Pretraining Corpora on In-context Learning by a Large-scale Language Model
Seongjin Shin, Sang-Woo Lee, Hwijeen Ahn +8
Many recent studies on large-scale language models have reported successful in-context zero- and few-shot learning ability. However, the in-depth analysis of when in-context learni…
Generating Information-Seeking Conversations from Unlabeled Documents
Gangwoo Kim, Sungdong Kim, Kang Min Yoo +1
In this paper, we introduce a novel framework, SIMSEEK, (Simulating information-Seeking conversation from unlabeled documents), and compare its two variants. In our baseline SIMSEE…
The Dialog Must Go On: Improving Visual Dialog via Generative Self-Training
Gi-Cheon Kang, Sungdong Kim, Jin-Hwa Kim +2
Visual dialog (VisDial) is a task of answering a sequence of questions grounded in an image, using the dialog history as context. Prior work has trained the dialog agents solely on…