Watermarking LLM-Generated Datasets in Downstream Tasks | Paper Citation Record

Observation f21f770a-5e0a-4e3d-9752-2142a82234c7 · outbound

This paper cites an unresolved cited work.

Watermarking LLM-Generated Datasets in Downstream Tasks Unresolved cited work

Reference 1

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:05:14.501622Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 294c8eda-43c8-45bf-b16e-4d6a01436ba1 · outbound

This paper cites an unresolved cited work.

Watermarking LLM-Generated Datasets in Downstream Tasks Unresolved cited work

Reference 2

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:05:14.491557Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 5e3f115b-32c4-45f9-a4bf-451414c47d55 · outbound

This paper cites an unresolved cited work.

Watermarking LLM-Generated Datasets in Downstream Tasks Unresolved cited work

Reference 3

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:05:14.481842Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c19b11aa-276c-40b6-99ef-578d70ed0d40 · outbound

This paper cites Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring.

Watermarking LLM-Generated Datasets in Downstream Tasks Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.471644Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6df6c065-0643-42fb-bdde-86fa61f206a5 · outbound

This paper cites Benchmarking Large Language Models in Retrieval- Augmented Generation.

Watermarking LLM-Generated Datasets in Downstream Tasks Benchmarking Large Language Models in Retrieval- Augmented Generation

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.461336Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation fc60c94e-7384-4928-b6cd-49388e42d49a · outbound

This paper cites BadNL: Backdoor Attacks Against NLP Models with Semantic-preserving Improvements.

Watermarking LLM-Generated Datasets in Downstream Tasks BadNL: Backdoor Attacks Against NLP Models with Semantic-preserving Improvements

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.451137Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 774ab2c9-0374-48a4-9c2c-2baff3bc92d2 · outbound

This paper cites REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data.

Watermarking LLM-Generated Datasets in Downstream Tasks REFIT: A Unified Watermark Removal Framework For Deep Learning Systems With Limited Data

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.440403Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 6f0ff7fa-4da7-4d74-b59b-41dfafd005db · outbound

This paper cites DialogSum: A Real-Life Scenario Dialogue Summarization Dataset.

Watermarking LLM-Generated Datasets in Downstream Tasks DialogSum: A Real-Life Scenario Dialogue Summarization Dataset

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.610432Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88fd7c3b-c086-431f-b272-11eaaff58099 · outbound

This paper cites Increasing Diversity While Maintaining Ac- curacy: Text Data Generation with Large Language Models and Human Interventions.

Watermarking LLM-Generated Datasets in Downstream Tasks Increasing Diversity While Maintaining Ac- curacy: Text Data Generation with Large Language Models and Human Interventions

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.429454Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation af7e8229-016b-4afa-ac9d-c8e2815257c4 · outbound

This paper cites SSL- Guard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders.

Watermarking LLM-Generated Datasets in Downstream Tasks SSL- Guard: A Watermarking Scheme for Self-supervised Learning Pre-trained Encoders

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.419129Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 56e007be-c73a-464c-8c80-590b81d401a1 · outbound

This paper cites BERT: Pre-training of Deep Bidi- rectional Transformers for Language Understanding.

Watermarking LLM-Generated Datasets in Downstream Tasks BERT: Pre-training of Deep Bidi- rectional Transformers for Language Understanding

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.410000Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ec1dbe64-129e-437f-ab22-bbb99306cbfb · outbound

This paper cites Watermark Removal Scheme Based on Neural Network Model Pruning.

Watermarking LLM-Generated Datasets in Downstream Tasks Watermark Removal Scheme Based on Neural Network Model Pruning

Reference 12

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.399935Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a8478f51-98b2-4f98-8bda-39ce046cf39b · outbound

This paper cites Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models.

Watermarking LLM-Generated Datasets in Downstream Tasks Fine-tuning Is Not Enough: A Simple yet Effective Watermark Removal Attack for DNN Models

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.388865Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation ece92ced-ce9c-40cd-93c3-ee64ab2a5edd · outbound

This paper cites Choquette-Choo, Varun Chandrasekaran, and Nicolas Papernot.

Watermarking LLM-Generated Datasets in Downstream Tasks Choquette-Choo, Varun Chandrasekaran, and Nicolas Papernot

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.377407Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 877653c0-1ad8-4410-bbe0-deecc15ca846 · outbound

This paper cites Watermark Stealing in Large Language Models.

Watermarking LLM-Generated Datasets in Downstream Tasks Watermark Stealing in Large Language Models

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.641762Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b370c68-d58e-44f9-ba5f-25ae2a105d08 · outbound

This paper cites A Watermark for Large Language Models.

Watermarking LLM-Generated Datasets in Downstream Tasks A Watermark for Large Language Models

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.365864Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation c7d9d5f9-7355-4407-ba33-36326f4ee8e9 · outbound

This paper cites On the Reliability of Watermarks for Large Language Models.

Watermarking LLM-Generated Datasets in Downstream Tasks On the Reliability of Watermarks for Large Language Models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.649880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6f3cb3ad-6ad4-4fd9-966d-496e4b041af5 · outbound

This paper cites Large Lan- guage Models are Zero-Shot Reasoners.

Watermarking LLM-Generated Datasets in Downstream Tasks Large Lan- guage Models are Zero-Shot Reasoners

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.354883Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1dd7d24e-7d69-48e8-98c3-b6cf94fc0119 · outbound

This paper cites Efficient Memory Management for Large Language Model Serving with PagedAttention.

Watermarking LLM-Generated Datasets in Downstream Tasks Efficient Memory Management for Large Language Model Serving with PagedAttention

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.658014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e2810871-7c1a-4425-bab5-c17a23e03708 · outbound

This paper cites Who Wrote this Code? Watermarking for Code Generation.

Watermarking LLM-Generated Datasets in Downstream Tasks Who Wrote this Code? Watermarking for Code Generation

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.343826Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 836de15c-2712-4e82-becc-cb8fdf2d9c94 · outbound

This paper cites PLMmark: A Se- cure and Robust Black-Box Watermarking Framework for Pre-trained Language Models.

Watermarking LLM-Generated Datasets in Downstream Tasks PLMmark: A Se- cure and Robust Black-Box Watermarking Framework for Pre-trained Language Models

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.334513Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation db8176b6-8302-4cad-89b0-934a440747f3 · outbound

This paper cites Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limita- tions.

Watermarking LLM-Generated Datasets in Downstream Tasks Synthetic Data Generation with Large Language Models for Text Classification: Potential and Limita- tions

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.325164Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 1cf380d7-8840-47db-87cd-04d15168c19a · outbound

This paper cites Mapping the Increasing Use of LLMs in Scientific Papers.

Watermarking LLM-Generated Datasets in Downstream Tasks Mapping the Increasing Use of LLMs in Scientific Papers

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.673700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5709cfbd-2ad9-4e83-bea5-9bbf95ab70ad · outbound

This paper cites A Semantic Invariant Robust Watermark for Large Language Models.

Watermarking LLM-Generated Datasets in Downstream Tasks A Semantic Invariant Robust Watermark for Large Language Models

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.314053Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d040c723-74a4-4a6a-898d-59b7abaeabcb · outbound

This paper cites Improved Baselines with Visual Instruction Tuning.

Watermarking LLM-Generated Datasets in Downstream Tasks Improved Baselines with Visual Instruction Tuning

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.681598Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b6d8041-2ee6-4f56-8685-68de15c1ea5d · outbound

This paper cites Fine-Pruning: Defending Against Backdooring At- tacks on Deep Neural Networks.

Watermarking LLM-Generated Datasets in Downstream Tasks Fine-Pruning: Defending Against Backdooring At- tacks on Deep Neural Networks

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.302410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a72c2e65-4f76-4a6f-98fb-7cae0e049107 · outbound

This paper cites RoBERTa: A Robustly Optimized BERT Pretraining Approach.

Watermarking LLM-Generated Datasets in Downstream Tasks RoBERTa: A Robustly Optimized BERT Pretraining Approach

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.693923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3474027f-9fcc-4880-8ed7-fb9e9ab6415f · outbound

This paper cites Robustness Over Time: Understanding Adversarial Examples’ Effective- ness on Longitudinal Versions of Large Language Mod- els.

Watermarking LLM-Generated Datasets in Downstream Tasks Robustness Over Time: Understanding Adversarial Examples’ Effective- ness on Longitudinal Versions of Large Language Mod- els

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.698022Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10c4be50-fcb6-4475-9dbd-659d3484340a · outbound

This paper cites Backdoor Attacks Against Dataset Distillation.

Watermarking LLM-Generated Datasets in Downstream Tasks Backdoor Attacks Against Dataset Distillation

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.701832Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f50ef0e8-70fc-4dd9-b5f6-e332d0090b9b · outbound

This paper cites Watermarking Diffusion Model.

Watermarking LLM-Generated Datasets in Downstream Tasks Watermarking Diffusion Model

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.705252Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c354a406-f805-408c-a260-2b2546571b17 · outbound

This paper cites SoK: How Robust is Image Classification Deep Neural Network Watermarking? In IEEE Sympo- sium on Security and Privacy (S&P).

Watermarking LLM-Generated Datasets in Downstream Tasks SoK: How Robust is Image Classification Deep Neural Network Watermarking? In IEEE Sympo- sium on Security and Privacy (S&P)

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.280560Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation dcc0d5b4-0601-453e-bbcc-9cb077d8fe75 · outbound

This paper cites Maas, Raymond E.

Watermarking LLM-Generated Datasets in Downstream Tasks Maas, Raymond E

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.269857Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 0e7d8361-3dd8-4824-921c-9facf154e29f · outbound

This paper cites Adversarial Frontier Stitching for Remote Neural Network Watermarking.

Watermarking LLM-Generated Datasets in Downstream Tasks Adversarial Frontier Stitching for Remote Neural Network Watermarking

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-08-15T20:05:13.926416Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation bfcd9b10-9cf4-498e-a29a-7b7d7eb7bf79 · outbound

This paper cites Protecting Intellectual Property of Generative Adversarial Networks From Ambiguity Attacks.

Watermarking LLM-Generated Datasets in Downstream Tasks Protecting Intellectual Property of Generative Adversarial Networks From Ambiguity Attacks

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.259070Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 90fc52f7-a726-444e-a1e3-a9fcbbe55770 · outbound

This paper cites GPT-4 Technical Report.

Watermarking LLM-Generated Datasets in Downstream Tasks GPT-4 Technical Report

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.723763Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 614a7207-2f59-4f95-ae2a-6d002ea92906 · outbound

This paper cites What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning.

Watermarking LLM-Generated Datasets in Downstream Tasks What In-Context Learning "Learns" In-Context: Disentangling Task Recognition and Task Learning

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.727499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f9ad02e8-5cd9-4a23-832e-55db64dde343 · outbound

This paper cites Hidden Trigger Backdoor Attack on NLP Models via Linguistic Style Manipulation.

Watermarking LLM-Generated Datasets in Downstream Tasks Hidden Trigger Backdoor Attack on NLP Models via Linguistic Style Manipulation

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.246216Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation be0a15fe-e27e-4156-80c2-caba2d995a77 · outbound

This paper cites No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices.

Watermarking LLM-Generated Datasets in Downstream Tasks No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.735365Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 19d1feb2-7c0b-42cb-a7ae-2ae20534a9a6 · outbound

This paper cites Can Large Language Models Rea- son about Program Invariants? In International Con- ference on Machine Learning (ICML).

Watermarking LLM-Generated Datasets in Downstream Tasks Can Large Language Models Rea- son about Program Invariants? In International Con- ference on Machine Learning (ICML)

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.235516Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation f5cfd16e-5c8f-40f8-88dc-f78535ddc13a · outbound

This paper cites Are You Copying My 16 Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark.

Watermarking LLM-Generated Datasets in Downstream Tasks Are You Copying My 16 Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermark

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.224841Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation a5f497f4-ec59-4027-8f15-a0d734377988 · outbound

This paper cites MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Fron- tiers.

Watermarking LLM-Generated Datasets in Downstream Tasks MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Fron- tiers

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.214225Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b377f731-04e0-4c54-b286-2852a122e48c · outbound

This paper cites an unresolved cited work.

Watermarking LLM-Generated Datasets in Downstream Tasks Unresolved cited work

Reference 42

Resolution: unresolved; raw_fallback, observed 2026-08-15T20:05:14.202873Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation d8b16b26-6ce3-487b-955f-d0137e1e9388 · outbound

This paper cites A Robust Semantics-based Watermark for Large Language Model against Paraphrasing.

Watermarking LLM-Generated Datasets in Downstream Tasks A Robust Semantics-based Watermark for Large Language Model against Paraphrasing

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.754604Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ecf92461-5a14-4a0d-84cf-e9ddfef10b5b · outbound

This paper cites DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models.

Watermarking LLM-Generated Datasets in Downstream Tasks DeepSigns: A Generic Watermarking Framework for IP Protection of Deep Learning Models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.758607Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4e038ada-5af4-43ac-a73e-ecc55d8aa876 · outbound

This paper cites Embedding Watermarks into Deep Neural Networks.

Watermarking LLM-Generated Datasets in Downstream Tasks Embedding Watermarks into Deep Neural Networks

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.190816Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 26ae3b52-3151-45fd-922c-db8fb6306290 · outbound

This paper cites Attacks on Digital Watermarks for Deep Neural Networks.

Watermarking LLM-Generated Datasets in Downstream Tasks Attacks on Digital Watermarks for Deep Neural Networks

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.180912Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 3cb94ae6-7c65-4d89-9f35-da10ce05c7b4 · outbound

This paper cites Chi, Quoc V.

Watermarking LLM-Generated Datasets in Downstream Tasks Chi, Quoc V

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.169288Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b765b2b0-a7d7-48d1-b9bc-540dcbd4e803 · outbound

This paper cites Qwen2 Technical Report.

Watermarking LLM-Generated Datasets in Downstream Tasks Qwen2 Technical Report

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.772794Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c964d4b0-05eb-47a1-867b-bd2f5b2e28ec · outbound

This paper cites Qwen2.5 Technical Report.

Watermarking LLM-Generated Datasets in Downstream Tasks Qwen2.5 Technical Report

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.776333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 42be5da1-8f5f-4cf2-a655-9585ca2a4fda · outbound

This paper cites Stoecklin, Heqing Huang, and Ian Molloy.

Watermarking LLM-Generated Datasets in Downstream Tasks Stoecklin, Heqing Huang, and Ian Molloy

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.157727Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 473fa5af-2c68-4bc6-b097-28e9e56a59f5 · outbound

This paper cites Instruction Backdoor Attacks Against Cus- tomized LLMs.

Watermarking LLM-Generated Datasets in Downstream Tasks Instruction Backdoor Attacks Against Cus- tomized LLMs

Reference 51

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.145588Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b95b7335-8f4d-4547-8b2f-a9bcadf61973 · outbound

This paper cites Character-level Convolutional Networks for Text Clas- sification.

Watermarking LLM-Generated Datasets in Downstream Tasks Character-level Convolutional Networks for Text Clas- sification

Reference 52

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.132555Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation b1acfadc-23f9-4dff-812b-c4c29bd25581 · outbound

This paper cites Provable Robust Watermarking for AI-Generated Text.

Watermarking LLM-Generated Datasets in Downstream Tasks Provable Robust Watermarking for AI-Generated Text

Reference 53

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.122309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 17b42f32-6dc5-4e3f-9f4b-d62e47324d90 · outbound

This paper cites Attention Distrac- tion: Watermark Removal Through Continual Learn- ing with Selective Forgetting.

Watermarking LLM-Generated Datasets in Downstream Tasks Attention Distrac- tion: Watermark Removal Through Continual Learn- ing with Selective Forgetting

Reference 54

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.110614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 309e7638-2de3-440d-bfb6-9128bdd7da02 · outbound

This paper cites Large Language Models are Human-Level Prompt En- gineers.

Watermarking LLM-Generated Datasets in Downstream Tasks Large Language Models are Human-Level Prompt En- gineers

Reference 55

Resolution: verified fuzzy; raw_fallback, observed 2026-08-15T20:05:14.099059Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 2e3487eb-5544-4941-8cc8-a28470d33ec7 · outbound

This paper cites MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models.

Watermarking LLM-Generated Datasets in Downstream Tasks MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-15T20:05:13.802572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d46fb075-40ed-4356-8f5c-66dd6a7fda23 · outbound

This paper cites To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression.

Watermarking LLM-Generated Datasets in Downstream Tasks To Prune, or Not to Prune: Exploring the Efficacy of Pruning for Model Compression

Reference 57

Resolution: malformed identifier; raw_fallback, observed 2026-08-15T20:05:14.088526Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Observation 13b20512-a735-4a35-9216-660dd4aaf8b1 · outbound

This paper cites an unresolved cited work.

Watermarking LLM-Generated Datasets in Downstream Tasks Unresolved cited work

Reference 294

Resolution: parse uncertain; raw_fallback, observed 2026-08-15T20:05:14.291279Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers