1 citations · 2 across the 12 of their papers we have counts for
5 papers · 1 filter
Empirical Analysis of Large Vision-Language Models against Goal Hijacking via Visual Prompt Injection
Subaru Kimura, Ryota Tanaka, Shumpei Miyawaki +2
We explore visual prompt injection (VPI) that maliciously exploits the ability of large vision-language models (LVLMs) to follow instructions drawn onto the input image. We propose…
The Curse of Popularity: Popular Entities have Catastrophic Side Effects when Deleting Knowledge from Language Models
Ryosuke Takahashi, Go Kamoda, Benjamin Heinzerling +2
Language models (LMs) encode world knowledge in their internal parameters through training. However, LMs may learn personal and confidential information from the training data, lea…
First Heuristic Then Rational: Dynamic Use of Heuristics in Language Model Reasoning
Yoichi Aoki, Keito Kudo, Tatsuki Kuribayashi +4
Multi-step reasoning instruction, such as chain-of-thought prompting, is widely adopted to explore better language models (LMs) performance. We report on the systematic strategy th…
ACORN: Aspect-wise Commonsense Reasoning Explanation Evaluation
Ana Brassard, Benjamin Heinzerling, Keito Kudo +2
Evaluating the quality of free-text explanations is a multifaceted, subjective, and labor-intensive task. Large language models (LLMs) present an appealing alternative due to their…
J-UniMorph: Japanese Morphological Annotation through the Universal Feature Schema
Kosuke Matsuzaki, Masaya Taniguchi, Kentaro Inui +1
We introduce a Japanese Morphology dataset, J-UniMorph, developed based on the UniMorph feature schema. This dataset addresses the unique and rich verb forms characteristic of the…