Whether an information extraction pipeline should process page images or parsed text depends on the document, and the answer flips across the layout spectrum. We study this trade-off under a constraint that rules out (closed) cloud services: privacy-sensitive documents processed on-premise by small ($\le 8\mathrm{B}$ p...
Christoph Walser, Mauricio Fadel Argerich, Jonathan Furst· 0 citations
Researchers increasingly use generative large language models (LLMs) to convert corporate text into empirical variables. We examine the extent to which LLM-based textual measures are invariant to model choice using thirteen measures, including sentiment, management clarity, uncertainty, answer specificity, and climate...
LAVOIR (Laya with Value-Of-Information Routing), which places the candidate pieces of missing information (slots) in the input next to the answer options, so that one forward pass returns both the decision distribution and, for every slot, the expected gain in the probability of the correct decision if the user were as...
Furkan Yilmaz, Habibe Aleyna Tasdemir, Muhammed Faruk Gozay· 1 citation
The present study profiled eight Serbian participants through a questionnaire, a deep interview, and a written self-presentation, recorded their reactions to sixty-eight social media posts, and asked four language models to predict those reactions under five prompt conditions varying profile content and instruction sty...
Ljubiša Bojić, Tijana Stanić, Joerg Matthes et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
The contribution is not a more accurate judge, but a label-free way to tell when a judge has no basis for its answer, which is a label-free way to tell when a judge has no basis for its answer.
Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a...
Phannet Pov, Hyun Woo Park, Voneat Pen et al.· 0 citations
Overall, persona prompting affects interpretive framing more strongly than descriptive grounding, and profile-pair similarity patterns are strongly correlated for all three output types, although agreement is lowest for justifications.
Neemias B. da Silva, Matt Ratto, Myriam Delgado et al.· 0 citations
Cascaded Automatic Speech Recognition - Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily because their decoupled design ensures perceptual verifiability. However, cascaded systems suffer from error propagation, as transcription failures inevitably cascade t...
Yizhou Peng, Ziyang Ma, Changsong Liu et al.· 0 citations
Agent evaluation requires assessing complex multi-step behaviors involving tool use and intermediate reasoning, making it costly and expertise-intensive. A natural question arises: can frontier coding assistants reliably automate this evaluation process? Our study shows that simply prompting coding assistants is insuff...
Kang Zhou, Sangmin Woo, Haibo Ding et al.· 0 citations
In Natural Language Processing (NLP) classification tasks where a lack of labeled data is an issue, continued pretraining (CPT) of transformer models on unlabeled data is an established approach. In this paper, we have two aims.
(1) We describe our observations from continued pretraining of the Finnish BERT transform...
Rami Luisto, Liisa Pet\"ainen, Tommi Gr\"onholm et al.· 0 citations
We introduce DiscoPhon, a multilingual benchmark for evaluating unsupervised phoneme discovery from discrete speech units. DiscoPhon covers 6 dev and 6 test languages, chosen to span a wide range of phonemic contrasts. Given only 10 hours of speech in a previously unseen language, systems must produce discrete units th...
Maxime Poli, Manel Khentout, Angelo Ortiz Tandazo et al.· 0 citations
Temporarily ambiguous garden-path sentences ("While the team trained the striker wondered... ") are known to cause processing difficulty, which can manifest itself in a variety of reading behaviors (in-situ slowdowns, rereading), as well as in miscomprehension or outright rejection of the sentence as ungrammatical. Whi...
Dario Paape, Tal Linzen, Shravan Vasishth· 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.
