6 papers
Hallucination Span Detection with Input-Side Evidence Alignment
Miyu Yamada, Yuki Arase
Hallucinations remain a major obstacle to the reliable use of large language models (LLMs) in conditional text generation. Existing methods primarily assess the factuality of an en…
Applicability Condition Extraction for Therapeutic Drug-Disease Relations
Guanting Luo, Noriki Nishida, Yuji Matsumoto +1
Identifying conditions that a certain drug takes therapeutic effect on a target disease is crucial for clinical decision-making support. However, most existing biomedical informati…
Adaptive LoRA Merge with Parameter Pruning for Low-Resource Generation
Ryota Miyano, Yuki Arase
This study proposes a simple yet effective LoRA merge method to achieve LLM adaptation for low-resource language generation tasks. The LoRA merge technique, which integrates multip…
Hallucinated Span Detection with Multi-View Attention Features
Yuya Ogasa, Yuki Arase
This study addresses the problem of hallucinated span detection in the outputs of large language models. It has received less attention than output-level hallucination detection de…
Edit-Constrained Decoding for Sentence Simplification
Tatsuya Zetsu, Yuki Arase, Tomoyuki Kajiwara
We propose edit operation based lexically constrained decoding for sentence simplification. In sentence simplification, lexical paraphrasing is one of the primary procedures for re…
Distilling Monolingual and Crosslingual Word-in-Context Representations
Yuki Arase, Tomoyuki Kajiwara
In this study, we propose a method that distils representations of word meaning in context from a pre-trained masked language model in both monolingual and crosslingual settings. W…