As natural language corpora expand at an unprecedented rate, manual annotation remains a significant methodological bottleneck in corpus linguistic work. We address this challenge by presenting a scalable pipeline for automating grammatical annotation in voluminous corpora using large language models (LLMs). Unlike pre...
Cameron Morin, Matti Marttinen Larsson· 0 citations
Socio-economic causal effects depend heavily on their institutional and environmental contexts. The same intervention can produce different, even opposite, effects across regulatory regimes, market conditions, time periods, or populations. This poses a challenge for large language models (LLMs) in decision-support role...
Donggyu Lee, Hyeok Yun, Meeyoung Cha et al.· 0 citations
Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second, multi-agent pipelines often dilute strong solutions by averaging across all candidate...
Xiangru Tang, Wanghan Xu, Yujie Wang et al.· 0 citations
Big5-Scaler is presented, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits that induces consistent and distinguishable personality traits across models, with performance varying by prompt type and scale.
A novel message encoding paradigm is proposed called \textit{majority bit-aware encoding}, which relaxes the watermark signal strength from the green list size, which allows for a strong watermark signal to be preserved in generated texts even when using a large green list.
Jiahao Xu, Rui Hu, O. Kotevska et al.· arXiv.org· 3 citations
Language models (LMs) are used for a diverse range of tasks, from question answering to writing fantastical stories. In order to reliably accomplish these tasks, LMs must be able to discern the modal category of a sentence (i.e., whether it describes something that is possible, impossible, completely nonsensical, etc.)...
Michael A. Lepori, Jennifer Hu, Ishita Dasgupta et al.· 0 citations
Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often falling into circular reasoning patterns or deviating from the logical path entirely. This limitation is particularly acute in retrieval-augment...
Chao Wan, Albert Gong, Mihir Mishra et al.· 0 citations
This study evaluates the effectiveness of ChatGPT, an advanced AI model for natural language processing, in identifying targeting and inappropriate language in online comments. With the increasing challenge of moderating vast volumes of user-generated content on social network sites, the role of AI in content moderatio...
Baran Barbarestani, Isa Maks, Piek Vossen· 0 citations
Automated research with LLM agents has shown promising results in various domains. Through iterative refinement and scored verifiers, LLM agents are capable of discovering new ideas. There are different ways to scale automated research: let one agent iterate for longer, run several agents in parallel, or further let th...
Shangyin Tan, Ben Zhou, Lakshya A Agrawal et al.· 0 citations
SwarmRSI is introduced, a framework that evolves scientific agent swarms for recursive self-improvement and proposes Feedback-Guided Swarm Mutation to refine hypotheses and their implementations using experimental feedback from other agents and Complementary Swarm Recombination to reuse retained hypotheses and compleme...
Qian-Ru Meng, Xi Zhang, Konstantinos Papakostas et al.· 0 citations
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obscures relevant evidence, making focused reasoning increasingly difficult. We introduce TreeFlex, a framework in which th...
Dong-Zhuo Li, Fang-Zhou Cheng, Wei-Wei Li et al.· 0 citations
Full-duplex speech systems must decide when to enter, hold, or relinquish the conversational floor, even as multiple speakers overlap or backchannel without taking it. Existing evaluations study dyadic turn-taking or end-to-end agent behavior, but lack a unified, controlled evaluation of genuine floor transitions again...
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.
