paper-with-me

Papers

Sniff AI: Is My 'Spicy' Your 'Spicy'? Exploring LLM's Perceptual Alignment with Human Smell Experiences

2024-11-11 · Shu Zhong, Zetao Zhou, Christopher Dawes, Giada Brianz, Marianna Obrist

Aligning AI with human intent is important, yet perceptual alignment-how AI interprets what we see, hear, or smell-remains underexplored. This work focuses on olfaction, human smell experiences. We conducted a user study with 40 participants to investigate how well AI can interpret human descriptions of scents. Participants performed "sniff and describe" interactive tasks, with our designed AI system attempting to guess what scent the participants were experiencing based on their descriptions. These tasks evaluated the Large Language Model's (LLMs) contextual understanding and representation of scent relationships within its internal states - high-dimensional embedding space. Both quantitative and qualitative methods were used to evaluate the AI system's performance. Results indicated limited perceptual alignment, with biases towards certain scents, like lemon and peppermint, and continued failing to identify others, like rosemary. We discuss these findings in light of human-AI alignment advancements, highlighting the limitations and opportunities for enhancing HCI systems with multisensory experience integration.

📄 PDF Abstract BibTeX arXiv:2411.06950

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

How do non-tastes taste? A corpus-based study on Chinese people’s perception of spicy and numbing food

2018-12-01 · PACLIC 2018 12 · Sicong Dong, Yin Zhong, Chu-Ren Huang

Will releasing the weights of future large language models grant widespread access to pandemic agents?

2023-10-25 · Anjali Gopal, Nathan Helm-Burger, Lennart Justen, Emily H. Soice 외

Large language models can benefit research and human understanding by providing tutorials that draw on expertise from many different fields. A properly safeguarded model will refuse to provide "dual-use" insights that co…

Spicy Salmon: Converting between 50+ Annotation Formats with Fintan, Pepper, Salt and Powla

2022-06-01 · LDL (ACL) 2022 6 · Christian Fäth, Christian Chiarcos

Heterogeneity of formats, models and annotations has always been a primary hindrance for exploiting the ever increasing amount of existing linguistic resources for real world applications in and beyond NLP. Fintan - the …

RuleWeaver: Benchmarking Rule-Centered Scenario Reasoning for Large Language Models

2026-08-27 · Bohan Yu, Shi-Yang Li, Pengfei Cao, Jun Zhao 외 arxiv

Large language models (LLMs) are increasingly applied to specialized domains, where effective use of domain expertise often requires reasoning over complex rules in concrete scenarios. However, existing benchmarks only p…

Exploring Dual-Sniffer Passive Localization: Algorithm Design and Experimental Results

2024-10-16 · Tuo Wu, Lingyu Hou, Hong Niu, Saihua Xu 외

In this paper, we explore a dual-sniffer passive localization system that detects the timing difference of signals from both commercial base station (eNb) and user equipment (UE) to the sniffers. We design two localizati…

Position