Document-level Information Extraction (DocIE) aims to produce an output template with the entities, relations, and events of interest occurring in the given document. Standard practices include prompting decoder-only LLMs using greedy decoding to avoid output variability. Rather than treating this variability as a limi...
Mikel Zubillaga, Oscar Sainz, Oier Lopez de Lacalle et al.· 0 citations
Confidence estimation (CE) indicates how reliable the answers of large language models are and impacts user trust and decision-making. Existing evaluations mainly concern the alignment between confidence and correctness, but ignore the variability of language: confidence estimates should remain consistent under semanti...
Yuxi Xia, Dennis Ulmer, Terra Blevins et al.· 0 citations
Most automatic speech processing systems operate in ``open loop'' mode without user feedback about who said what, yet human-in-the-loop workflows can potentially enable higher accuracy. We propose an LLM-assisted in-meeting speaker correction system that lets users fix speaker attribution errors through brief correctiv...
Xinlu He, Yiwen Guan, Badrivishal Paurana et al.· 0 citations
Often, multilingual language models are trained with the objective to map semantically similar content (in different languages) in the same latent space. In this paper, we show a nuance in this training objective, and find that by changing the language of the input query, we can improve the question answering ability o...
Ishika Agarwal, Nimet Beyza Bozdag, Dilek Hakkani-T\"ur· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This comprehensive study evaluates the performance of OpenAI's o1-preview large language model across a diverse array of complex reasoning tasks, spanning multiple domains, including computer science, mathematics, natural sciences, medicine, linguistics, and social sciences. Through rigorous testing, o1-preview demonst...
Tianyang Zhong, Zhengliang Liu, Yi Pan et al.· 0 citations
This work introduces SVGLM, a framework that uses scalable vector graphics (SVG) primitives to connect text and image in reasoning tasks, and exploits the duality of SVG as both image description and text instructions, yielding a more compact, interpretable solution to equip general VLMs with the capability of generati...
Sun-Li Chen, Ding Zhong, Ziqiao Ma et al.· 0 citations
STRAND is introduced, a benchmark of human-verified object-centric facts that evaluates intermediate reasoning by decomposing queries into sub-questions, distinguishing genuine temporal understanding from coincidental correctness and an object-centric framework that explicitly constructs and reasons over structured obj...
T. Nguyen, C. Trinh, Khoi M. Le et al.· 0 citations
An embodied scene question-answering (QA) interface in which vision never enters the language model is studied, showing the gain survives paraphrase, attributing it to decision-aligned computation rather than answer-string leakage, while novel judgment vocabularies bound its scope.
A pipeline for building an open-taxonomy semantic annotation of source code using a code-specialised Large Language Model, and a calibrated quality-assurance protocol that quantifies annotation precision by combining a small human gold set with an LLM-as-a-judge filter are presented.
Federico Pennino, Andrea Gurioli, Stefano Zacchiroli et al.· 1 citation
This work proposes accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions for one synthetic voice rendered in both languages, so the voice cancels and only the accent remains.
A personalized Korean visual speech recognition (VSR) system is presented and the gap between the population-level benchmark score and an individual user's error is quantified, on the nine-camera OLKAVS corpus.
Se Un Park, Hak-seon Kim, Tae-Hoon Roh et al.· 0 citations
It is demonstrated that the CTC-weighted language model log likelihood ratio can be interpreted as the KLD between the unknown correct ASR and the unsupervised learned ASR, and that, using a Pinsker bound, the square root of KLD can be interpreted as an upper bound on the total variation distance between the true and e...
Meng-Qi Wang, Mark A. Hasegawa-Johnson, Hao-Long Zheng 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.
