Cool Papers · cs.CL (papers.cool) · RSS 摘要

信源：Cool Papers · cs.CL (papers.cool) · https://papers.cool/arxiv/cs.CL/feed

• The Language of Instruction: Genre and Generative AI — This article argues that instruction-fine-tuned language models should be understood as implementing a genre, what is proposed as the instructional-conversational genre. This genr…
• Measure Before You Train: Typed Decision Models vs. a Classical Baseline vs. a Generative LLM for Routing a Personal Multilingual Inbox — Personal email agents decide, for every message, what it is, whether it is urgent, whether to draft a reply, create a task, or ignore it. Their error rate is rarely measured: the …
• Yalda-Embedding: Open Development of a Competitive Persian Retrieval Model — Despite advances in multilingual text representations, effective dense retrieval for Persian remains constrained by the limited availability of language-specific training resource…
• Adaptive Frequency Threshold Byte Pair Encoding for Mixed Natural Language and Structured Symbolic Corpora — Modern language models rely on subwording tokenization to define the discrete units of input processing, typically using methods like Byte Pair Encoding (BPE) that treat whitespac…
• J-Comm: Jacobian-Guided Latent Communication between LLM Agents — Latent communication requires both an effective continuous reasoning process and an interface through which an external model can leverage its intermediate computation. We present…