Paper

On the Persistent Effects of Lexicality in Large Language Mod

Unreadunread

AI summary

arXiv:2606. 02750v1 Announce Type: new Abstract: Representations extracted from large language models (LLMs) play an important role in many downstream applications.

Reading status

Priority

About this paper

Authors: Hammad Rizwan, Muhammad Umair Haider, Nishant Subramani, Mona T. Diab, A. B. Siddique, Hassan Sajjad
Released: 2026-06-03 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because On the Persistent Effects of Lexicality in Large Language Mod overlaps with 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)", clean result "The marker is a representational handle, not a behavioural one — sharing it between a villain persona and the assistant transfers no misalignment (HIGH confidence)", experiment "Follow-up to #354: cascading chunk-binding — does A→B, B→C, C→D propagate the full chain on a recipient trained only to emit A?". Matching terms: under, rate, trained, test, language, model. Source: arxiv cs.CL (NLP).
arXiv: 2606.02750

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to On the Persistent Effects of Lexicality in Large Language Mod. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.