5 papers
Looking in the Mirror: Introspecting Side-Effect Misalignments Induced by Fine-Tuning
Kotaro Yoshida, Laura Gomezjurado Gonzalez, Yukinori Yamamoto +3
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation…
DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
Kotaro Yoshida, Yuji Naraki, Takafumi Horie +2
Model merging has emerged as an efficient and flexible paradigm for multi-task learning, with numerous methods being proposed in recent years. However, these state-of-the-art techn…
On Fairness of Task Arithmetic: The Role of Task Vectors
Hiroki Naganuma, Kotaro Yoshida, Laura Gomezjurado Gonzalez +3
Model editing techniques, particularly task arithmetic with task vectors, offer an efficient alternative to full fine-tuning by enabling direct parameter updates through simple ari…
LegalRikai: Open Benchmark -- Benchmark for Complex Japanese Corporate Legal Tasks
Shogo Fujita, Yuji Naraki, Yiqing Zhu +1
This paper introduces LegalRikai: Open Benchmark, a new benchmark comprising four complex tasks that emulate Japanese corporate legal practices. The benchmark was created by legal…
Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation
Yuji Naraki, Ryosuke Yamaki, Yoshikazu Ikeda +4
In the field of Natural Language Processing (NLP), Named Entity Recognition (NER) is recognized as a critical technology, employed across a wide array of applications. Traditional…