Paper

Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis

Unreadunread

AI summary

arXiv:2605. 15440v1 Announce Type: new Abstract: Surprisal theory posits that the processing difficulty of a word is determined by its predictability in context, offering a potential link between human sentence processing and next-word predictions from language models.

Reading status

Priority

About this paper

Authors: William Timkey, Brian Dillon, Tal Linzen
Released: 2026-05-18 (2mo ago)
Topic: Related to current project
Relation to my work: Read next because Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, word, under, compare, control, full, test, language. Source: arxiv cs.CL (NLP).
arXiv: 2605.15440

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Why are language models less surprised than humans? Testing the Parse Multiplicity Mismatch Hypothesis. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.