Search Results for author:
Found 11 papers, 7 papers with code
KL Penalty Control via Perturbation for Direct Preference Optimization
Direct Preference Optimization (DPO) demonstrates the advantage of aligning a large language model with human preference using only an offline dataset.
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
Specifically, by viewing the autoencoder of LDM as a downsampling-upsampling kernel, HFI measures the extent of aliasing, a distortion of high-frequency information that appears in the reconstructed image.
EXAONE 3.5: Series of Large Language Models for Real-world Use Cases
This technical report introduces the EXAONE 3. 5 instruction-tuned language models, developed and released by LG AI Research.
Efficient Dynamic Hard Negative Sampling for Dialogue Selection
Recent studies have demonstrated significant improvements in selection tasks, and a considerable portion of this success is attributed to incorporating informative negative samples during training.
Ranked #1 on
Conversational Response Selection
on E-commerce
EXAONE 3.0 7.8B Instruction Tuned Language Model
We introduce EXAONE 3. 0 instruction-tuned language model, the first open model in the family of Large Language Models (LLMs) developed by LG AI Research.
Deep Exploration of Cross-Lingual Zero-Shot Generalization in Instruction Tuning
Subsequently, we assess the performance on unseen tasks in a language different from the one used for training.
Instruction Matters: A Simple yet Effective Task Selection for Optimized Instruction Tuning of Specific Tasks
In this light, we introduce a simple yet effective task selection method that leverages instruction information alone to identify relevant tasks, optimizing instruction tuning for specific tasks.
Lightweight feature encoder for wake-up word detection based on self-supervised speech representation
Self-supervised learning method that provides generalized speech representations has recently received increasing attention.
External Knowledge Selection with Weighted Negative Sampling in Knowledge-grounded Task-oriented Dialogue Systems
In the experiment, we investigate the effect of weighted negative sampling, post-training, and style transfer.
Towards Continual Knowledge Learning of Language Models
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.
Extrofitting: Enriching Word Representation and its Vector Space with Semantic Lexicons
The method consists of 3 steps as follows: (i) Expanding 1 or more dimension(s) on all the word vectors, filling with their representative value.
