Digital cultural heritage collections encode rich relations among objects, places, periods, providers, images, and source institutions, yet users typically access them through keyword search and faceted browsing. We present CULTUREBOT, an interactive framework for natural-language exploration of cultural heritage colle...
Vasileios Karampinis, Angelos Vlachos, Giorgos Filandrianos et al.· 0 citations
Although users may express different personalization needs across tasks, these task-specific behaviors can reflect shared underlying preference mechanisms. Existing LLM personalization methods often focus on surface-level interactions or undifferentiated histories, overlooking the shared mechanisms underlying these beh...
Hang Su, Ze-Qun Liu, Jiang-Han Chao et al.· 0 citations
Large language models are increasingly deployed in morally and legally sensitive contexts, yet little is known about how they internally represent distinctions between moral reasoning styles. We ask whether a model's differential response to rule-framed and consequence-framed moral questions reflects distinct internal...
Multilingual translation requires a model to preserve meaning while producing text in a requested language. We present HexaBee-4B, a translator adapted from Gemma 3 4B IT through three stages: Wikipedia continued pretraining, joint multilingual answering and answer-text translation, and bidirectional translation specia...
Iman Barati, Mohammadmostafa Rostamkhani, Mohammad Badzohreh· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
On-policy self-distillation (OPSD) trains a large language model using supervision from a teacher instantiated from the same model as the student. The teacher is conditioned on privileged information (PI), such as verified solutions. The student, which does not observe PI, learns from the teacher's next-token distribut...
Jiazheng Li, Yawei Li, Jun-Ru Lu et al.· 0 citations
Large language models (LLMs) can reduce hallucination by abstaining from questions they would likely get wrong. Abstention can be implemented outside the model (selective answering) using a confidence threshold that controls the answer rate (coverage), or learned inside it (abstention training), which can perform bette...
Jun-Wei Zhang, Yi-Fei Wang, Wan-Li Yang et al.· 0 citations
Language models trained only on text from before a given year are useful for studying hindsight and historical language, but the open collections of pre-modern Chinese carry no publication dates and unreliable dynasty labels. We present L\"ushi-1840, a 983M-parameter model trained from scratch on 12,262 books (1.28B ch...
This manuscript presents DeepThink, a knowledge-addressable framework for recurrent language modeling. A Knowledge Bank stores typed Knowledge Units, a Knowledge Activator selects units from the current execution state, Knowledge Assembly produces an executable configuration, and a Shared Thinking Operator updates that...
ScaleMAS is built, where asynchronous agents interact with a shared datastore of linked messages via three operations: publishing messages with optional references to earlier ones that they build on, searching for messages by content, and visiting messages by address, which is an effective proxy for quality.
Zhen-Ting Qi, Zhuo-Kai Zhao, Ru-Lin Shao et al.· 0 citations
Humans are increasingly using large language models (LLMs) in decision making processes throughout society. Unfortunately, models have biases, and these can be very difficult to measure, especially in closed-weight models. For example, 'green washed' models may produce reinforcement learned responses but, in pressure s...
For context-based question answering, using one large model for both evidence extraction and answer reasoning requires substantial memory and computation. Existing approaches trade accuracy for efficiency within a single model only. We propose a multi-model approach for efficient inference: our method, PAIR, employs tw...
Sejun Park, Haocheng Xia, Yongjoo Park· 0 citations
Emotion datasets are routinely mapped onto positive and negative valence, by assigning each emotion category one polarity. We test where this works and where it fails, using SemEval-2018 Affect in Tweets (English, Arabic, Spanish), Affective Text aligned with EmoBank, raw GoEmotions annotations, naturalistic hashtag co...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
