Pre-trained language models (PLMs) with encoder-based architectures have shown impressive capabilities in zero-shot cross-lingual transfer for various language understanding tasks. However, applying this technique to dependency parsing remains a significant challenge due to its syntactic nature. To boost model generali...
Lalita Lowphansirikul, Attapol Rutherford, Jian Gang Ngui et al.· 0 citations
AnthroDial is introduced, a unified framework for developing anthropomorphic social agents from three complementary aspects: MindFlow, a lightweight interaction harness that enables autonomous, asynchronous, and adaptive communication through a dynamic Mind Buffer; CAPS-Eval, a theory-grounded framework for evaluating...
Wen-Tao Liu, Xi Chen, Si-Yu Song et al.· 0 citations
Vision-Language Models (VLMs) remain vulnerable to cross-modal implicit risks: visual and textual inputs that appear benign in isolation can jointly elicit unsafe responses. Existing safety methods often require large preference datasets, costly multi-rollout training, or additional safeguards at inference time. They m...
Haotian Deng, Wenbin Xing, Gang Xu et al.· 0 citations
SCSP is a training-free framework that leverages semantic compression for informative token selection in long-context embedding and can be integrated into both zero-shot and fine-tuned models in a plug-and-play manner, consistently improving their performance.
Zi-Feng Cheng, Jie Zheng, Zhiwei Jiang et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Purpose: Most Greek papyri remain unpublished and undigitised; a handwritten text recognition (HTR) pipeline that transcribes them automatically would let scholars discover documents and literary works that have so far gone unread. Recognition systems for Ancient Greek papyri are in statu nascendi, and how accurate the...
Existing product matching benchmarks primarily contain English-language product data and are often dominated by a single product category, such as electronics. This paper introduces Billiger.de Products, a bilingual German and English entity matching benchmark covering thirteen consumer product categories, including di...
Aaron Steiner, Ksenia Elagin, Ralph Peeters et al.· 0 citations
Reading behaviour varies not only with linguistic input, but also with reader proficiency. In this study, we investigate whether the layer-wise relationship between surprisal from large language models (LLMs) and human gaze behaviour differs across readers with different levels of proficiency and across gaze measures....
Akio Hayakawa, Horacio Saggion· Conference on Empirical Meth...· 0 citations
Graph-based retrieval-augmented generation supports multi-hop retrieval by organizing corpus information into graphs. However, existing relation-free graph retrieval methods rely primarily on query-sentence similarity to search for evidence. This can exclude useful bridging evidence with low query similarity and activa...
LLMs have been studied in recent linguistics as potential models of humans'linguistic abilities. Here we discuss an entirely different use of AI, namely as a co-scientist, to help construct and assess linguistic theories (we refer to the result as"Co-Linguistics"). Since the 1960s, linguistics has developed theories th...
E. Chemla, B. Spector, Alexandros Kalomoiros et al.· 0 citations
Judges should be assessed on rank-gap-conditional metrics, ideally against human rankings, and this argument is formalized and validated in a controlled simulation and on two human-rated corpora.
Audio-visual large language models (AVLLMs) have made remarkable progress in multimodal understanding and reasoning through interactions among visual, auditory, and linguistic information. However, recent studies show that AVLLMs face a critical challenge: $\textbf{source-confused grounding hallucination}$, where cues...
Yu Zhang, Ping Zhang, Xue-Feng Bai et al.· 1 citation
Merging pretrained models has emerged as an effective approach for consolidating diverse capabilities into a single unified model. However, prevailing merging methods typically treat each task vector as an indivisible merging unit, overlooking the heterogeneous geometric changes encoded within it. This treatment can in...
Zijing Wang, Yongkang Liu, Mingyang Wang 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.
