Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning | Paper Citation Record

Observation eb6cdc65-12a3-4d12-b3e5-53ba31e2e5d4 · outbound

This paper cites Second-order stochastic optimization for machine learn- ing in linear time.Journal of Machine Learning Re- search, 18(116):1–40, 2017.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Second-order stochastic optimization for machine learn- ing in linear time.Journal of Machine Learning Re- search, 18(116):1–40, 2017

Reference 1

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2bcaf717-ea6d-4fee-af20-bdbae7a3fe18 · outbound

This paper cites Can generative ai models extract deeper sentiments as compared to tra- ditional deep learning algorithms?IEEE Intelligent Systems, 39(2):5–10, 2024.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Can generative ai models extract deeper sentiments as compared to tra- ditional deep learning algorithms?IEEE Intelligent Systems, 39(2):5–10, 2024

Reference 2

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8715a95c-df98-4b2d-84e6-49e30d5ff37e · outbound

This paper cites PaLM 2 Technical Report.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning PaLM 2 Technical Report

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.071036Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 017ad96d-deef-4c4f-85cd-ee4aadef2a25 · outbound

This paper cites Introducing claude 4, 2025.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Introducing claude 4, 2025

Reference 4

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3e43d48-4a40-44cb-a3a4-b58de0e1679f · outbound

This paper cites Summarizing news: Unleashing the power of bart, gpt-2, t5, and pega- sus models in text summarization.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Summarizing news: Unleashing the power of bart, gpt-2, t5, and pega- sus models in text summarization

Reference 5

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e0c3564-e684-4db9-9d68-d95c1e2fca1c · outbound

This paper cites Guardbench: A large-scale benchmark for guardrail models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Guardbench: A large-scale benchmark for guardrail models

Reference 6

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a460fa0f-ac02-4304-ab12-e1ab8408329c · outbound

This paper cites Machine un- learning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Machine un- learning

Reference 7

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fa1a6ca-daf1-4c37-afc4-38dc141431a9 · outbound

This paper cites TweetNLP: Cutting- edge natural language processing for social media.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning TweetNLP: Cutting- edge natural language processing for social media

Reference 8

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 21f23894-dfd2-4887-8a1e-804062c50691 · outbound

This paper cites Towards making systems forget with machine unlearning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Towards making systems forget with machine unlearning

Reference 9

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99404189-b224-4ed4-8ffc-f3d91a07dd68 · outbound

This paper cites Pruning strategies for back- door defense in llms.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Pruning strategies for back- door defense in llms

Reference 10

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ad9c5a94-9ac6-452a-a2df-ea6ac76042cc · outbound

This paper cites Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering

Reference 11

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.065668Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 4148720e-0ace-4a26-b293-9344d0057875 · outbound

This paper cites A thorough examination of the cnn/daily mail reading comprehension task.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning A thorough examination of the cnn/daily mail reading comprehension task

Reference 12

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6551c652-8c50-4a92-8cad-dc99ecf998d2 · outbound

This paper cites Badnl: Backdoor attacks against nlp mod- els with semantic-preserving improvements.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Badnl: Backdoor attacks against nlp mod- els with semantic-preserving improvements

Reference 13

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5372bdf6-70da-4d83-b404-26668075350a · outbound

This paper cites Sdd: Self-degraded defense against malicious fine-tuning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Sdd: Self-degraded defense against malicious fine-tuning

Reference 14

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1dc83893-e269-410e-b3c3-fa4726ce4d21 · outbound

This paper cites Gonzalez, Ion Stoica, and Eric P.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Gonzalez, Ion Stoica, and Eric P

Reference 15

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9877d1e3-c170-4415-be7c-e36bddd9c430 · outbound

This paper cites Forget unlearning: Towards true data-deletion in machine learning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Forget unlearning: Towards true data-deletion in machine learning

Reference 16

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6fa6a541-c059-4f34-9112-2555d47400f6 · outbound

This paper cites Scaling instruction-finetuned language models.Journal of Ma- chine Learning Research, 25(70):1–53, 2024.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Scaling instruction-finetuned language models.Journal of Ma- chine Learning Research, 25(70):1–53, 2024

Reference 17

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8b79489f-2f02-42b5-8f7d-6c3e064b7112 · outbound

This paper cites A discourse-aware attention model for ab- stractive summarization of long documents.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning A discourse-aware attention model for ab- stractive summarization of long documents

Reference 18

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5bdd9a06-8376-473f-98ec-263e898bc906 · outbound

This paper cites Certi- fied adversarial robustness via randomized smoothing.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Certi- fied adversarial robustness via randomized smoothing

Reference 19

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 596f4fe6-3124-4e8c-9167-17590ea19007 · outbound

This paper cites Wikisum: Coherent summariza- tion dataset for efficient human-evaluation.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Wikisum: Coherent summariza- tion dataset for efficient human-evaluation

Reference 20

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58798f41-fe66-4aa1-a634-2b0cf5a593d3 · outbound

This paper cites Structured in- formation extraction from scientific text with large lan- guage models.Nature communications, 15(1):1418, 2024.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Structured in- formation extraction from scientific text with large lan- guage models.Nature communications, 15(1):1418, 2024

Reference 21

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 085f207d-352b-4699-ae43-8a4fdd126162 · outbound

This paper cites The llama 3 herd of models.arXiv e-prints, pages arXiv–2407, 2024.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning The llama 3 herd of models.arXiv e-prints, pages arXiv–2407, 2024

Reference 22

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d26b0f0c-3249-416d-b92f-b3d9c271c123 · outbound

This paper cites The algorithmic foun- dations of differential privacy.Foundations and Trends® in Theoretical Computer Science, 9(3-4):211–407, 2014.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning The algorithmic foun- dations of differential privacy.Foundations and Trends® in Theoretical Computer Science, 9(3-4):211–407, 2014

Reference 23

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cb190af6-bf31-4fd3-afd1-7fceaaf526e6 · outbound

This paper cites HotFlip: White-Box Adversarial Examples for Text Classification.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning HotFlip: White-Box Adversarial Examples for Text Classification

Reference 24

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.079511Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation ceef7bcf-d751-4c81-88c2-64ed180275e3 · outbound

This paper cites Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model

Reference 25

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2d052db2-aced-467e-b990-516d610f2259 · outbound

This paper cites Attack to defend: Exploiting adversarial attacks for detecting poisoned models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Attack to defend: Exploiting adversarial attacks for detecting poisoned models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 59e1d459-1d79-4969-8dc0-f3e59754a0f4 · outbound

This paper cites Strip: A de- fence against trojan attacks on deep neural networks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Strip: A de- fence against trojan attacks on deep neural networks

Reference 27

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0384e2a3-83be-4efa-8fb7-e30b1fd6baf6 · outbound

This paper cites Eternal sunshine of the spotless net: Selective forgetting in deep networks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Eternal sunshine of the spotless net: Selective forgetting in deep networks

Reference 28

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2dbfdf83-15b9-4978-b07e-0ca57429a07c · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Explaining and Harnessing Adversarial Examples

Reference 29

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.068340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation b618a2f9-77cf-492e-8d44-5274e06388cf · outbound

This paper cites Flight of the pegasus? comparing transformers on few- shot and zero-shot multi-document abstractive summa- rization.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Flight of the pegasus? comparing transformers on few- shot and zero-shot multi-document abstractive summa- rization

Reference 30

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b3d9ddff-11f9-4200-bec9-5ad98c99f817 · outbound

This paper cites Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Countering the Effects of Lead Bias in News Summarization via Multi-Stage Training and Auxiliary Losses

Reference 31

Resolution: verified exact; arxiv_id, observed 2026-07-04T21:00:09.051813Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f45b68c8-867a-4531-ab5a-4aa649a44926 · outbound

This paper cites Certified data removal from machine learning models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Certified data removal from machine learning models

Reference 32

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bf36c18c-9d13-4d8d-9c27-986ac4ee862e · outbound

This paper cites Adaptive machine unlearning.Advances in Neural Information Processing Systems, 34:16319–16330, 2021.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Adaptive machine unlearning.Advances in Neural Information Processing Systems, 34:16319–16330, 2021

Reference 33

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 06e861f1-6c54-4178-bbc2-adfbaa049e75 · outbound

This paper cites Generative language models exhibit social identity bi- ases.Nature Computational Science, 5(1):65–75, 2025.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Generative language models exhibit social identity bi- ases.Nature Computational Science, 5(1):65–75, 2025

Reference 34

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6023ad4b-0e64-4280-8ba0-a298e6ca15c1 · outbound

This paper cites Adaptive defense against harmful fine- tuning for large language models via bayesian data scheduler.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Adaptive defense against harmful fine- tuning for large language models via bayesian data scheduler

Reference 35

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 425aa7f7-7c9d-468c-b649-78da44e0ffff · outbound

This paper cites Antidote: Post-fine- tuning safety alignment for large language models against harmful fine-tuning attack.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Antidote: Post-fine- tuning safety alignment for large language models against harmful fine-tuning attack

Reference 36

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05feafc3-1995-4c38-90f8-2491ebbdbc38 · outbound

This paper cites GPT-4o System Card.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning GPT-4o System Card

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.074486Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6295a362-6327-4e33-8720-0c47aa62a8c7 · outbound

This paper cites Knowledge unlearning for mitigating privacy risks in language models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Knowledge unlearning for mitigating privacy risks in language models

Reference 38

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 10ee2f34-39af-40fc-b267-daf7dd461da1 · outbound

This paper cites Mistral 7B.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Mistral 7B

Reference 39

Resolution: malformed identifier; local_arxiv, observed 2026-07-04T21:00:09.077139Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 3024e743-2020-4bb0-987e-c36fb0d896f9 · outbound

This paper cites Is bert really robust? a strong baseline for nat- ural language attack on text classification and entailment.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Is bert really robust? a strong baseline for nat- ural language attack on text classification and entailment

Reference 40

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 87c6c9d6-2a48-4069-a441-3628fd0abf56 · outbound

This paper cites Understanding black- box predictions via influence functions.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Understanding black- box predictions via influence functions

Reference 41

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9427311d-93f9-4f49-bfae-6d4e888a041e · outbound

This paper cites Gender bias and stereotypes in large language models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Gender bias and stereotypes in large language models

Reference 42

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a3430c7-0467-42a9-b943-4bb73bacd6aa · outbound

This paper cites Investigating implicit bias in large language models: A large-scale study of over 50 llms.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Investigating implicit bias in large language models: A large-scale study of over 50 llms

Reference 43

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9eb4bb5e-e7eb-472a-89c2-bdae45c6695d · outbound

This paper cites Datainf: Efficiently estimating data influence in lora- tuned llms and diffusion models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Datainf: Efficiently estimating data influence in lora- tuned llms and diffusion models

Reference 44

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 35267433-e757-4b32-a2e1-8b0e64cc8947 · outbound

This paper cites BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

Reference 45

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.057166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation 6dbc112e-4b3b-4a5e-910c-4939b81a766f · outbound

This paper cites Efficiently generat- ing sentence-level textual adversarial examples with seq2seq stacked auto-encoder.Expert Systems with Ap- plications, 213:119170, 2023.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Efficiently generat- ing sentence-level textual adversarial examples with seq2seq stacked auto-encoder.Expert Systems with Ap- plications, 213:119170, 2023

Reference 46

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9a245af-0ed9-4f97-9182-795eb49698c2 · outbound

This paper cites Text adver- sarial purification as defense against adversarial attacks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Text adver- sarial purification as defense against adversarial attacks

Reference 47

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00527617-a8b4-4279-a9cc-fd79fe46a0b8 · outbound

This paper cites ROUGE: A package for automatic eval- uation of summaries.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning ROUGE: A package for automatic eval- uation of summaries

Reference 48

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 705915d7-bc53-4a85-a97d-bcb7b81c4a1a · outbound

This paper cites Joint character-level word embedding and adversarial stability training to defend adversarial text.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Joint character-level word embedding and adversarial stability training to defend adversarial text

Reference 49

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76192794-276b-4873-8313-b65c68c26edd · outbound

This paper cites On learning to summarize with large language models as references.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning On learning to summarize with large language models as references

Reference 50

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dcd95374-5a56-4937-98dc-26baad1c9538 · outbound

This paper cites Modality- aware neuron pruning for unlearning in multi- modal large language models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Modality- aware neuron pruning for unlearning in multi- modal large language models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e790fcd0-dc66-459f-b762-dbd741870966 · outbound

This paper cites Multi-xscience: A large-scale dataset for extreme multi-document sum- marization of scientific articles.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Multi-xscience: A large-scale dataset for extreme multi-document sum- marization of scientific articles

Reference 52

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 07012f10-eb41-48ee-89d7-dbbdffac9ff3 · outbound

This paper cites Towards deep learning models resistant to adversarial attacks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Towards deep learning models resistant to adversarial attacks

Reference 53

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation eaca5dd9-6842-43bf-ad9c-654eda596969 · outbound

This paper cites Adversarial training methods for semi-supervised text classification.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Adversarial training methods for semi-supervised text classification

Reference 54

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d3e48206-941d-41c5-b006-7081bb440440 · outbound

This paper cites Adversarial text purification: A large language model approach for defense.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Adversarial text purification: A large language model approach for defense

Reference 55

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation aa6f6014-46f1-41a3-9719-6a9510bd085e · outbound

This paper cites Sum- marunner: A recurrent neural network based sequence model for extractive summarization of documents.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Sum- marunner: A recurrent neural network based sequence model for extractive summarization of documents

Reference 56

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ece11160-796d-4913-897d-e4ed3b4b30fe · outbound

This paper cites A survey of machine unlearning.ACM Transactions on Intelligent Systems and Technology, 16(5):1–46, 2025.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning A survey of machine unlearning.ACM Transactions on Intelligent Systems and Technology, 16(5):1–46, 2025

Reference 57

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation da74e412-a538-4612-8967-3f006dab3404 · outbound

This paper cites Textguard: Provable defense against backdoor attacks on text classification.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Textguard: Provable defense against backdoor attacks on text classification

Reference 58

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 278bc3f8-ec6c-463e-95e7-c3e872bdf02e · outbound

This paper cites Estimating training data influence by trac- ing gradient descent.Advances in Neural Information Processing Systems, 33:19920–19930, 2020.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Estimating training data influence by trac- ing gradient descent.Advances in Neural Information Processing Systems, 33:19920–19930, 2020

Reference 59

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4cd1474f-cbf0-4c59-8472-431b07b48f7c · outbound

This paper cites an unresolved cited work.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Unresolved cited work

Reference 60

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b6139d6-89c8-449a-80d0-b55642919784 · outbound

This paper cites Exploring the limits of transfer learn- ing with a unified text-to-text transformer.The Journal of Machine Learning Research, 21(1):5485–5551, 2020.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Exploring the limits of transfer learn- ing with a unified text-to-text transformer.The Journal of Machine Learning Research, 21(1):5485–5551, 2020

Reference 61

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5cf47f4a-def2-4249-a204-bc84b0353150 · outbound

This paper cites On context utilization in summarization with large language models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning On context utilization in summarization with large language models

Reference 62

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e4f0803-b9b8-457f-971f-e89d44c70762 · outbound

This paper cites Sentence-bert: Sen- tence embeddings using siamese bert-networks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Sentence-bert: Sen- tence embeddings using siamese bert-networks

Reference 63

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d7fe8151-a442-4c28-b39e-391335b69533 · outbound

This paper cites Representation nois- ing: A defence mechanism against harmful finetuning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Representation nois- ing: A defence mechanism against harmful finetuning

Reference 64

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 05269805-6e05-447a-b53b-87f087ddb29a · outbound

This paper cites Immuniza- tion against harmful fine-tuning attacks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Immuniza- tion against harmful fine-tuning attacks

Reference 65

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e4103cd9-8fe7-4bfb-a527-03caf9de8517 · outbound

This paper cites A maximum entropy approach to adaptive statistical language modelling.Computer speech and language, 10(3):187, 1996.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning A maximum entropy approach to adaptive statistical language modelling.Computer speech and language, 10(3):187, 1996

Reference 66

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99b8ab68-0135-4a69-844d-48f00c324692 · outbound

This paper cites Rome was built in 1776: A case study on factual correctness in knowledge-grounded response generation.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Rome was built in 1776: A case study on factual correctness in knowledge-grounded response generation

Reference 67

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 130c25af-84da-4724-b614-3d3281f06508 · outbound

This paper cites Evaluating performance of transformer models for dialogue summarization: A comparison of t5-base, t5-small, and bart-base.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Evaluating performance of transformer models for dialogue summarization: A comparison of t5-base, t5-small, and bart-base

Reference 68

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f974e4a5-314e-4471-bc53-c93878745f27 · outbound

This paper cites Textshield: Beyond successfully detecting adversarial 17 sentences in text classification.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Textshield: Beyond successfully detecting adversarial 17 sentences in text classification

Reference 69

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4c5ce92e-f228-4751-9d22-c1245623397f · outbound

This paper cites what shapes your bias?.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning what shapes your bias?

Reference 70

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c7968ac6-0cce-4617-93f2-4f4d0053762e · outbound

This paper cites Peftguard: detecting backdoor attacks against parameter- efficient fine-tuning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Peftguard: detecting backdoor attacks against parameter- efficient fine-tuning

Reference 71

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73c731f6-9c06-44b6-ae50-08ec02b5d5ed · outbound

This paper cites Fever: a large-scale dataset for fact extraction and verification.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Fever: a large-scale dataset for fact extraction and verification

Reference 72

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c0e1d12-c5f7-4b1c-80ba-c6dfd9a890e9 · outbound

This paper cites Attacks against abstractive text summarization models through lead bias and influence functions.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Attacks against abstractive text summarization models through lead bias and influence functions

Reference 73

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9287bb55-6600-4410-8209-c1c8fd7c8ce4 · outbound

This paper cites Unrolling sgd: Understanding factors influencing machine unlearning.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Unrolling sgd: Understanding factors influencing machine unlearning

Reference 74

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc86b16-7391-47f4-9068-8c46a60de85b · outbound

This paper cites Spectral signatures in backdoor attacks.Advances in neural information processing systems, 31, 2018.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Spectral signatures in backdoor attacks.Advances in neural information processing systems, 31, 2018

Reference 75

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47c48506-8041-41f5-bcc9-d3b18c4e1c1b · outbound

This paper cites Concealed data poisoning attacks on nlp models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Concealed data poisoning attacks on nlp models

Reference 76

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cafa6457-c87a-4018-bb4b-9bbedbb10e71 · outbound

This paper cites Neu- ral cleanse: Identifying and mitigating backdoor attacks in neural networks.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Neu- ral cleanse: Identifying and mitigating backdoor attacks in neural networks

Reference 77

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cebed54e-308f-49c0-a0a0-c2881f677261 · outbound

This paper cites SemAttack: Natural Textual Attacks via Different Semantic Spaces.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning SemAttack: Natural Textual Attacks via Different Semantic Spaces

Reference 78

Resolution: verified exact; arxiv_id, observed 2026-07-04T21:00:09.059395Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation a55c1db1-8af1-4364-b880-4a0a44169e1a · outbound

This paper cites Improving neural language modeling via adversarial training.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Improving neural language modeling via adversarial training

Reference 79

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8504d6ef-1482-432c-8a91-1d735c30b35c · outbound

This paper cites Mitigating data poisoning in text classification with differential privacy.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Mitigating data poisoning in text classification with differential privacy

Reference 80

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f6377c5-2f90-4e56-bea1-e8374137fb63 · outbound

This paper cites Qwen3 Technical Report.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Qwen3 Technical Report

Reference 81

Resolution: verified exact; local_arxiv, observed 2026-07-04T21:00:09.062250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-04T06:34:03.388597+00:00.

Observation f259fb7c-ccc8-4188-840d-36b5b72e486e · outbound

This paper cites Machine unlearn- ing of pre-trained large language models.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Machine unlearn- ing of pre-trained large language models

Reference 82

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d2b888f-35e3-48d4-984b-e9486d07ea90 · outbound

This paper cites Clibe: Detecting dynamic back- doors in transformer-based nlp models.Network and Distributed System Security (NDSS) Symposium, 2025.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Clibe: Detecting dynamic back- doors in transformer-based nlp models.Network and Distributed System Security (NDSS) Symposium, 2025

Reference 83

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68dcc53c-46e6-4cc4-adee-956a5aba0717 · outbound

This paper cites Alignscore: Evaluating factual consistency with a uni- fied alignment function.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Alignscore: Evaluating factual consistency with a uni- fied alignment function

Reference 84

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a99210a0-48a1-406f-b701-9b3714026f2d · outbound

This paper cites Pegasus: Pre-training with extracted gap-sentences for abstractive summarization.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning Pegasus: Pre-training with extracted gap-sentences for abstractive summarization

Reference 85

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation abfeb607-acb4-4e1a-a089-96ba257b2be5 · outbound

This paper cites A comprehensive survey of abstractive text summarization based on deep learning.Computa- tional intelligence and neuroscience, 2022(1):7132226, 2022.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning A comprehensive survey of abstractive text summarization based on deep learning.Computa- tional intelligence and neuroscience, 2022(1):7132226, 2022

Reference 86

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01b46de1-a663-4e0b-a616-68470f0e2f70 · outbound

This paper cites silicon nanowire design.

Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning silicon nanowire design

Reference 87

Resolution: unresolved; no resolver link, observed 2026-06-25T19:19:50.420396Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers