Signals 4 · free daily AI digest

A Formal Limitation on Learning Human Language From Textual Corpora

Paper recorded by Signals 4 on 2026-08-28 in cs.CL. Abstract reproduced from arXiv; link to the original below.

Published 2026-08-28 on arXiv · recorded by Signals 4 on 2026-08-31

Category: cs.CL · 自然语言处理 · first seen 2026-08-31

Abstract

Can a listener recover what a speaker means from the form of an utterance alone? We answer this question information-theoretically, and for a listener given by any featurizer of text, including the hidden states of contemporary large language models. Modeling language use as a joint distribution over meanings, contexts, and utterances, we derive upper bounds on the probability that a decoder recov

Read on arXiv →

#171 most recent of 186 cs.CL papers we have recorded · ↑ newer: Argument-Aware Semantic Alignment of Normative Texts: A Toulmin-Based · ↓ older: Phoneme- and Word-Level Metrics Using Self-Supervised Speech Represent
Cite this page: A Formal Limitation on Learning Human Language From Textual Corpora: the #171 most recent of 186 cs.CL papers we have recorded (as of 2026-08-28). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/a-formal-limitation-on-learning-human-language-from-textual-corpora.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.CL papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions