Shared by @hackernoon.com ↗
Shared by @NaihaoDeng ↗
aclanthology.org4d ago
Shared by @stanfordnlp ↗aclanthology.org7d agoSpeculative decoding greatly increases the interactivity of autoregressive language models by trading off computation for extra tokens generated in a single forward pass. Factorized draft models are especially efficient because they predict future-token m
arxiv.org·Twitter AI (high signal)·7d ago·1 min readMuch of the knowledge encoded in transformer language models (LMs) may be expressed in terms of relations: relations between words and their synonyms, entities and their attributes, etc. We show that, for a subset of relations, this computation is well-ap
arxiv.org·Twitter AI·9d ago·1 min readLinear-attention and state-space language models compress the prefix into a fixed-size recurrent state, yielding O(1) memory at the cost of a lossy exact memory: when many key--value associations compete, earlier facts are overwritten and needle recall de
Shared by @omarsar0 ↗arxiv.org13d agoExisting prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is often spread across multiple locations and connected through both local syntactic dependencies and global
Shared by @news.karthihegde.dev ↗arxiv.org14d agoLarge language models are often used to answer queries grounded in large text corpora (e.g. codebases, legal documents, or chat histories) by placing the entire corpus in the context window and leveraging in-context learning (ICL). Although current models
Shared by @cwolferesearch ↗arxiv.org15d agoOn-policy distillation (OPD) offers superior capacity transfer by supervising student-sampled trajectories with dense token-level signals. To furnish high-quality supervision sources and thereby elevate the performance frontier of distillation, an intuiti
Shared by @teortaxesTex ↗arxiv.org17d agoEvaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. W
Shared by @omarsar0 ↗arxiv.org19d ago
Shared by @huggingface ↗Speech and Language Processing
Shared by @stanfordnlp ↗In-context learning (ICL) has become the default method for using large language models (LLMs), making the exploration of its limitations and understanding the underlying causes crucial. In this paper, we find that ICL falls short of handling specificatio
Shared by @ai-linkstream.bsky.social ↗arxiv.org26d agoLarge language models (LLMs) are commonly prompted and interfaced with human-readable natural language, even when the intended reader is another model. This paper investigates whether semantic information can be encoded in compact, non-standard textual fo
Shared by @yuias.bsky.social ↗arxiv.org27d agoDiffusion Language Models (DLMs) have demonstrated strong scaling capacity as alternatives to autoregressive language models. However, their performance is highly sensitive to the choice of transition kernels, and poorly designed kernels can lead to issue
Shared by @ai-firehose.column.social ↗arxiv.org1mo ago
