REVIEW 3 cited by
WAPITI: A Watermark for Finetuned Open-Source LLMs
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
read the original abstract
Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs, as it enables traceability, accountability, and detection of manipulated content, helping to mitigate unintended consequences. However, for open-source models, watermarking faces two major challenges: (i) incompatibility with fine-tuned models, and (ii) vulnerability to fine-tuning attacks. In this work, we propose WAPITI, a new method that transfers watermarking from base models to fine-tuned models through parameter integration. To the best of our knowledge, we propose the first watermark for fine-tuned open-source LLMs that preserves their fine-tuned capabilities. Furthermore, our approach offers an effective defense against fine-tuning attacks. We test our method on various model architectures and watermarking strategies. Results demonstrate that our method can successfully inject watermarks and is highly compatible with fine-tuned models. Additionally, we offer an in-depth analysis of how parameter editing influences the watermark strength and overall capabilities of the resulting models.
Forward citations
Cited by 3 Pith papers
-
Saffron-1: Safety Inference Scaling
A multifurcation reward model that scores all next-token candidates in one call makes inference-time safety scaling with tree search far more compute-efficient than best-of-N sampling.
-
AdaDecode: Accelerating LLM Decoding with Adaptive Layer Parallelism
AdaDecode speeds up LLM generation by predicting tokens at early layers when confidence is high, running the skipped layers in parallel, and verifying the output exactly matches standard decoding.
-
Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning
Self-Error-Instruct clusters a model's math errors into types, synthesizes targeted practice data per type, and selects the best samples for fine-tuning, improving held-out math test accuracy.
Discussion (0). Sign in to comment.