1 code implementation • 14 Mar 2024 • Hyunji Lee, Doyoung Kim, Jihoon Jun, Sejune Joo, Joel Jang, Kyoung-Woon On, Minjoon Seo
Especially, the robustness of parametric token space which is established during the pretraining step tends to effectively enhance the stability of nonparametric sequence embedding space, a new space established by another language model.
no code implementations • 19 Jan 2024 • Dongkeun Yoon, Joel Jang, Sungdong Kim, Seungone Kim, Sheikh Shafayat, Minjoon Seo
We introduce LangBridge, a zero-shot approach to adapt language models for multilingual reasoning tasks without multilingual supervision.
2 code implementations • 17 Nov 2023 • Hamish Ivison, Yizhong Wang, Valentina Pyatkin, Nathan Lambert, Matthew Peters, Pradeep Dasigi, Joel Jang, David Wadden, Noah A. Smith, Iz Beltagy, Hannaneh Hajishirzi
Since the release of T\"ULU [Wang et al., 2023b], open resources for instruction tuning have developed quickly, from better base models to new finetuning techniques.
1 code implementation • 15 Nov 2023 • Hyunji Lee, Sejune Joo, Chaeeun Kim, Joel Jang, Doyoung Kim, Kyoung-Woon On, Minjoon Seo
Reliance on the inherent knowledge of Large Language Models (LLMs) can cause issues such as hallucinations, lack of control, and difficulties in integrating variable knowledge.
1 code implementation • 17 Oct 2023 • Joel Jang, Seungone Kim, Bill Yuchen Lin, Yizhong Wang, Jack Hessel, Luke Zettlemoyer, Hannaneh Hajishirzi, Yejin Choi, Prithviraj Ammanabrolu
In this work, we study Reinforcement Learning from Personalized Human Feedback (RLPHF) problem, wherein LLMs are aligned to multiple (sometimes conflicting) preferences by modeling alignment as a Multi-Objective Reinforcement Learning (MORL) problem.
2 code implementations • 12 Oct 2023 • Seungone Kim, Jamin Shin, Yejin Cho, Joel Jang, Shayne Longpre, Hwaran Lee, Sangdoo Yun, Seongjin Shin, Sungdong Kim, James Thorne, Minjoon Seo
We first construct the Feedback Collection, a new dataset that consists of 1K fine-grained score rubrics, 20K instructions, and 100K responses and language feedback generated by GPT-4.
1 code implementation • 12 Jun 2023 • Dongkeun Yoon, Joel Jang, Sungdong Kim, Minjoon Seo
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 enhances its zero-shot generalization capabilities across diverse NLP tasks.
no code implementations • 27 May 2023 • Soyoung Yoon, Chaeeun Kim, Hyunji Lee, Joel Jang, Sohee Yang, Minjoon Seo
Benchmarking the performance of information retrieval (IR) methods are mostly conducted with a fixed set of documents (static corpora); in realistic scenarios, this is rarely the case and the document to be retrieved are constantly updated and added.
1 code implementation • 24 May 2023 • Sohee Yang, Jonghyeon Kim, Joel Jang, Seonghyeon Ye, Hyunji Lee, Minjoon Seo
Previous works in prompt engineering for large language models have introduced different gradient-free probability-based prompt selection methods that aim to choose the optimal prompt among the candidates for a given task but have failed to provide a comprehensive and fair comparison between each other.
2 code implementations • 23 May 2023 • Seungone Kim, Se June Joo, Doyoung Kim, Joel Jang, Seonghyeon Ye, Jamin Shin, Minjoon Seo
Furthermore, we show that instruction tuning with CoT Collection allows LMs to possess stronger few-shot learning capabilities on 4 domain-specific tasks, resulting in an improvement of +2. 24% (Flan-T5 3B) and +2. 37% (Flan-T5 11B), even outperforming ChatGPT utilizing demonstrations until the max length by a +13. 98% margin.
Ranked #1 on on BIG-bench (SNARKS)
Common Sense Reasoning Common Sense Reasoning (Zero-Shot) +7
2 code implementations • 7 Feb 2023 • Joel Jang, Seungone Kim, Seonghyeon Ye, Doyoung Kim, Lajanugen Logeswaran, Moontae Lee, Kyungjae Lee, Minjoon Seo
Recently, Language Models (LMs) instruction-tuned on multiple tasks, also known as multitask-prompted fine-tuning (MT), have shown the capability to generalize to unseen tasks.
Ranked #9 on Question Answering on StoryCloze
1 code implementation • 6 Oct 2022 • Seonghyeon Ye, Doyoung Kim, Joel Jang, Joongbo Shin, Minjoon Seo
Meta-training, which fine-tunes the language model (LM) on various downstream tasks by maximizing the likelihood of the target label given the task instruction and input instance, has improved the zero-shot task generalization performance.
Ranked #2 on Question Answering on StoryCloze
1 code implementation • 6 Oct 2022 • Seonghyeon Ye, Joel Jang, Doyoung Kim, Yongrae Jo, Minjoon Seo
Enhancing the zero-shot performance of instruction-following models requires heavy computation, either by scaling the total number of training datasets or the model size.
1 code implementation • 4 Oct 2022 • Joel Jang, Dongkeun Yoon, Sohee Yang, Sungmin Cha, Moontae Lee, Lajanugen Logeswaran, Minjoon Seo
Pretrained Language Models (LMs) memorize a vast amount of knowledge during initial pretraining, including information that may violate the privacy of personal lives and identities.
Ranked #3 on Language Modelling on The Pile (Test perplexity metric)
1 code implementation • 26 Sep 2022 • Joel Jang, Seonghyeon Ye, Minjoon Seo
Previous work has shown that there exists a scaling law between the size of Language Models (LMs) and their zero-shot performance on different downstream NLP tasks.
3 code implementations • 31 May 2022 • Eunbi Choi, Yongrae Jo, Joel Jang, Minjoon Seo
Through these explorations, we show that PI can be a promising direction for conditioning language models, especially in scenarios with long and fixed prompts.
1 code implementation • 29 Apr 2022 • Joel Jang, Seonghyeon Ye, Changho Lee, Sohee Yang, Joongbo Shin, Janghoon Han, Gyeonghun Kim, Minjoon Seo
Language Models (LMs) become outdated as the world changes; they often fail to perform tasks requiring recent factual information which was absent or different during training, a phenomenon called temporal misalignment.
2 code implementations • ICLR 2022 • Joel Jang, Seonghyeon Ye, Sohee Yang, Joongbo Shin, Janghoon Han, Gyeonghun Kim, Stanley Jungkyu Choi, Minjoon Seo
By highlighting the critical causes of knowledge forgetting, we show that CKL is a challenging and important problem that helps us better understand and train ever-changing LMs.
no code implementations • 1 Jan 2021 • Joel Jang, Yoonjeon Kim, Jaewoo Kang
Classification tasks require balanced distribution of data in order to ensure the learner to be trained to generalize over all classes.
no code implementations • 20 Nov 2020 • Joel Jang, Yoonjeon Kim, Kyoungho Choi, Sungho Suh
Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes.