Zobrazeno 1 - 10
of 86
pro vyhledávání: '"Han, Seungju"'
Autor:
Chung, Jiwan, Lee, Sungjae, Kim, Minseo, Han, Seungju, Yousefpour, Ashkan, Hessel, Jack, Yu, Youngjae
Visual arguments, often used in advertising or social causes, rely on images to persuade viewers to do or believe something. Understanding these arguments requires selective vision: only specific visual stimuli within an image are relevant to the arg
Externí odkaz:
http://arxiv.org/abs/2406.18925
Autor:
Jiang, Liwei, Rao, Kavel, Han, Seungju, Ettinger, Allyson, Brahman, Faeze, Kumar, Sachin, Mireshghallah, Niloofar, Lu, Ximing, Sap, Maarten, Choi, Yejin, Dziri, Nouha
We introduce WildTeaming, an automatic LLM safety red-teaming framework that mines in-the-wild user-chatbot interactions to discover 5.7K unique clusters of novel jailbreak tactics, and then composes multiple tactics for systematic exploration of nov
Externí odkaz:
http://arxiv.org/abs/2406.18510
Autor:
Han, Seungju, Rao, Kavel, Ettinger, Allyson, Jiang, Liwei, Lin, Bill Yuchen, Lambert, Nathan, Choi, Yejin, Dziri, Nouha
We introduce WildGuard -- an open, light-weight moderation tool for LLM safety that achieves three goals: (1) identifying malicious intent in user prompts, (2) detecting safety risks of model responses, and (3) determining model refusal rate. Togethe
Externí odkaz:
http://arxiv.org/abs/2406.18495
Autor:
Lee, Seungbeen, Lim, Seungwon, Han, Seungju, Oh, Giyeong, Chae, Hyungjoo, Chung, Jiwan, Kim, Minju, Kwak, Beong-woo, Lee, Yeonsoo, Lee, Dongha, Yeo, Jinyoung, Yu, Youngjae
The idea of personality in descriptive psychology, traditionally defined through observable behavior, has now been extended to Large Language Models (LLMs) to better understand their behavior. This raises a question: do LLMs exhibit distinct and cons
Externí odkaz:
http://arxiv.org/abs/2406.14703
Despite the recent advances of the artificial intelligence, building social intelligence remains a challenge. Among social signals, laughter is one of the distinctive expressions that occurs during social interactions between humans. In this work, we
Externí odkaz:
http://arxiv.org/abs/2312.09818
Autor:
Han, Seungju, Choi, Mahn-Soo
We study the coupling of two topologcal subsystems in distinct topological states, and show that it leads to a precursor behavior of the topological phase transition in the overall system. This behavior is solely determined by the symmetry classes of
Externí odkaz:
http://arxiv.org/abs/2311.11673
Autor:
Han, Seungju, Kim, Junhyeok, Hessel, Jack, Jiang, Liwei, Chung, Jiwan, Son, Yejin, Choi, Yejin, Yu, Youngjae
Commonsense norms are defeasible by context: reading books is usually great, but not when driving a car. While contexts can be explicitly described in language, in embodied scenarios, contexts are often provided visually. This type of visually ground
Externí odkaz:
http://arxiv.org/abs/2310.10418
Visual information is central to conversation: body gestures and physical behaviour, for example, contribute to meaning that transcends words alone. To date, however, most neural conversational models are limited to just text. We introduce CHAMPAGNE,
Externí odkaz:
http://arxiv.org/abs/2303.09713
Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated responses,
Externí odkaz:
http://arxiv.org/abs/2210.05725
We consider two-dimensional superconductor/ferromagnet/superconductor junctions and investigate the subgap modes along the junction interface. The subgap modes exhibit characteristics similar to the Yu-Shiba-Rusinov states that originate form the int
Externí odkaz:
http://arxiv.org/abs/2210.04558