Search Results for author: Yuu Jinnai

Found 19 papers, 11 papers with code

Does Cross-Cultural Alignment Change the Commonsense Morality of Language Models?

no code implementations24 Jun 2024 Yuu Jinnai

In particular, we focus on evaluating whether the commonsense morality of the resulting fine-tuned models is aligned with Japanese culture using the JCommonsenseMorality (JCM) and ETHICS datasets.

Ethics Language Modelling

Annotation-Efficient Preference Optimization for Language Model Alignment

1 code implementation22 May 2024 Yuu Jinnai, Ukyo Honda

Instead of exhaustively annotating preference over all available response texts, AEPO selects a subset of responses that maximizes quality and diversity from the available responses, and then annotates preference over the selected ones.

Diversity Language Modelling

Filtered Direct Preference Optimization

1 code implementation22 Apr 2024 Tetsuro Morimura, Mitsuki Sakamoto, Yuu Jinnai, Kenshi Abe, Kaito Ariu

This paper addresses the issue of text quality within the preference dataset by focusing on direct preference optimization (DPO), an increasingly adopted reward-model-free RLHF method.

Regularized Best-of-N Sampling to Mitigate Reward Hacking for Language Model Alignment

1 code implementation1 Apr 2024 Yuu Jinnai, Tetsuro Morimura, Kaito Ariu, Kenshi Abe

In this research, we propose Regularized Best-of-N (RBoN), a variant of BoN that aims to mitigate reward hacking by incorporating a proximity term in response selection, similar to preference learning techniques.

Language Modelling

Generating Diverse and High-Quality Texts by Minimum Bayes Risk Decoding

1 code implementation10 Jan 2024 Yuu Jinnai, Ukyo Honda, Tetsuro Morimura, Peinan Zhang

We propose two variants of MBR, Diverse MBR (DMBR) and $k$-medoids MBR (KMBR), methods to generate a set of sentences with high quality and diversity.

Decoder Diversity +3

Hyperparameter-Free Approach for Faster Minimum Bayes Risk Decoding

1 code implementation5 Jan 2024 Yuu Jinnai, Kaito Ariu

Minimum Bayes-Risk (MBR) decoding is shown to be a powerful alternative to beam search decoding for a wide range of text generation tasks.

Image Captioning Machine Translation +3

Model-Based Minimum Bayes Risk Decoding for Text Generation

1 code implementation9 Nov 2023 Yuu Jinnai, Tetsuro Morimura, Ukyo Honda, Kaito Ariu, Kenshi Abe

MBR decoding selects a hypothesis from a pool of hypotheses that has the least expected risk under a probability model according to a given utility function.

Decoder Text Generation

On the Depth between Beam Search and Exhaustive Search for Text Generation

no code implementations25 Aug 2023 Yuu Jinnai, Tetsuro Morimura, Ukyo Honda

To this end, we introduce Lookahead Beam Search (LBS), a multi-step lookahead search that optimizes the objective considering a fixed number of future steps.

Machine Translation Text Generation +2

Blind Signal Separation for Fast Ultrasound Computed Tomography

no code implementations27 Apr 2023 Takumi Noda, Yuu Jinnai, Naoki Tomii, Takashi Azuma

The empirical result shows that FastUSCT significantly improves the quality of the image under the same imaging time to the conventional USCT method, especially when the imaging time is limited.

Lipschitz Lifelong Reinforcement Learning

1 code implementation15 Jan 2020 Erwan Lecarpentier, David Abel, Kavosh Asadi, Yuu Jinnai, Emmanuel Rachelson, Michael L. Littman

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks.

reinforcement-learning Reinforcement Learning (RL) +1

AlphaX: eXploring Neural Architectures with Deep Neural Networks and Monte Carlo Tree Search

1 code implementation26 Mar 2019 Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca

Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time.

Image Captioning Neural Architecture Search +4

Finding Options that Minimize Planning Time

no code implementations16 Oct 2018 Yuu Jinnai, David Abel, D. Ellis Hershkowitz, Michael Littman, George Konidaris

We formalize the problem of selecting the optimal set of options for planning as that of computing the smallest set of options so that planning converges in less than a given maximum of value-iteration passes.

Policy and Value Transfer in Lifelong Reinforcement Learning

no code implementations ICML 2018 David Abel, Yuu Jinnai, Sophie Yue Guo, George Konidaris, Michael Littman

We consider the problem of how best to use prior experience to bootstrap lifelong learning, where an agent faces a series of task instances drawn from some task distribution.

reinforcement-learning Reinforcement Learning (RL)

Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search

2 code implementations18 May 2018 Linnan Wang, Yiyang Zhao, Yuu Jinnai, Yuandong Tian, Rodrigo Fonseca

Neural Architecture Search (NAS) has shown great success in automating the design of neural networks, but the prohibitive amount of computations behind current NAS methods requires further investigations in improving the sample efficiency and the network evaluation cost to get better results in a shorter time.

Image Captioning Neural Architecture Search +4

A Survey of Parallel A*

1 code implementation16 Aug 2017 Alex Fukunaga, Adi Botea, Yuu Jinnai, Akihiro Kishimoto

A* is a best-first search algorithm for finding optimal-cost paths in graphs.

On Hash-Based Work Distribution Methods for Parallel Best-First Search

no code implementations10 Jun 2017 Yuu Jinnai, Alex Fukunaga

We show that Abstract Zobrist hashing outperforms previous methods on search domains using hand-coded, domain specific feature projection functions.

graph partitioning

Cannot find the paper you are looking for? You can Submit a new open access paper.