Diffusion language models (DLMs) generate text through iterative denoising, enabling bidirectional context modeling and parallel token refinement. Recent studies have applied reinforcement learning (RL) to DLMs and improved their reasoning performance. However, the iterative denoising process makes credit assignment mo...
Hongze Chen, Miao Pan, Lizhou Liang et al.· 0 citations
Given that the Chinese are one of the oldest ethnic groups to immigrate to the US, their cuisine have become central to the US dining scene and an interesting avenue to study how Chinese immigrants have culturally adapted into American life. In that regard, previous research has focused on analyzing the English names t...
Hang Jiang, Nanxi Liu, Tiantian Wang et al.· 0 citations
Large language models (LLMs) are increasingly used for codebook-based content analysis in computational social science, where codebooks translate theoretical concepts into labeling schemes. While prior work reports strong predictive performance, it remains unclear whether these systems produce reliable and robust text...
Elena Senger, Yuri Campbell, Rob van der Goot et al.· 0 citations
The value of language models for any community depends on whether a model actually understands the culture of the people it intends to serve. We use the Igbo language as a case study. Existing benchmarks test translated Western ideas, lacking depth. To address this, we introduce CAB-Igbo, a benchmark developed from ind...
Blessing Ngozi Uzor, Valdini Douglace Lemofouet, P. Anyanwu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models (LLMs) often produce plausible but incorrect answers, motivating reinforcement learning methods that reward correct answers, penalize incorrect answers, and allow abstention. However, fixed outcome-based rewards do not distinguish incorrect responses with different confidence levels or account for...
Qianchi Zhang, Hainan Zhang, Liang Pang et al.· 0 citations
Multilingual transformer models are often assumed to generalise across languages, but their effectiveness for coreference resolution in low-resource settings remains unverified. We investigate this gap in Bengali, a language with over 250 million speakers but limited annotated coreference resources. We evaluate transfo...
Large language models operationalize an intuitive, view of meaning as use. We argue that it faces a rule-following challenge. Using Kripke's interpretation of Wittgenstein, we argue that finite histories of use do not determine a unique rule for future extension. This reframes the debate about OOD generalization but al...
Niyar R Barman, Omar Naim, Nicholas Asher· 0 citations
Synthetic supervision can bootstrap semantic parsers in new search domains, but prompt-induced diversity is useful only when generations are faithful to the structured intent. We explore this for cold-start e-commerce search: 118,098 synthetic pairs produced by 6 LLMs with 9 persona-conditioned prompt families on a 47-...
Filippos Ventirozos, Tom Armitage, Mahmoud Oshagh et al.· 0 citations
Implicit misogyny often requires background knowledge to be understood. To address this challenge, we propose a Retrieval-Augmented Generation (RAG) framework for detecting and explaining implicit misogyny in English and Italian, leveraging encyclopedic, slang and feminist knowledge sources. Using the ImplicIT-Mis and...
Ivana Crescenzi, Arianna Muti, Maarten Sap et al.· 0 citations
AI assistants are increasingly asked to reason over a user's own web traces: group chats, community threads, activity logs and revision histories. On CL-bench Life, a benchmark of such real-life context learning, frontier LLMs solve fewer than one task in five. We find that the request is not the specification: over 80...
Jinhu Qi, Minda Hu, Wentao Zhang et al.· 0 citations
The Conflict of Skills Attack (CoSA) is introduced, which adds locally admitted Skills to an existing pool to supply missing business operations or reshape artifact exchange, decision reuse, and target/action bindings (relationship reshaping).
Yu-Jian Zheng, Tian-Hao Li, Shang-Zhi Xu et al.· 0 citations
Transportation agencies maintain extensive crash databases to identify safety priorities, evaluate countermeasures, and guide resource allocation. Making these data accessible to practitioners requires flexible ways to translate analytical questions into reliable results. Existing dashboards support predefined analyses...
Jing-Wen Zhu, Keshu Wu, Steven T. Parker et al.· 0 citations
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.
