Pith. sign in

REVIEW 1 cited by

Advancing Beyond Identification: Multi-bit Watermark for Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.00221 v3 pith:PNVZG6NQ submitted 2023-08-01 cs.CL cs.AIcs.CR

classification cs.CLcs.AIcs.CR
keywords messageswatermarkembeddinglanguagemulti-bitwithoutzero-bitbeyond
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
abstract

We show the viability of tackling misuses of large language models beyond the identification of machine-generated text. While existing zero-bit watermark methods focus on detection only, some malicious misuses demand tracing the adversary user for counteracting them. To address this, we propose Multi-bit Watermark via Position Allocation, embedding traceable multi-bit information during language model generation. Through allocating tokens onto different parts of the messages, we embed longer messages in high corruption settings without added latency. By independently embedding sub-units of messages, the proposed method outperforms the existing works in terms of robustness and latency. Leveraging the benefits of zero-bit watermarking, our method enables robust extraction of the watermark without any model access, embedding and extraction of long messages ($\geq$ 32-bit) without finetuning, and maintaining text quality, while allowing zero-bit detection all at the same time. Code is released here: https://github.com/bangawayoo/mb-lm-watermarking

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Watermarking Needs Input Repetition Masking

    cs.LG 2025-04 conditional novelty 6.0 of 10

    Conversational mimicry, especially reuse of prompt phrases, can make unwatermarked LLM text test positive for watermarks, and the paper argues current watermark configurations are too permissive.

Pith tools