Typed states for the displayed outbound observations.
Source: paper_references, paper_reference_links, observed 2026-08-15T21:01:51.951512Z
Paper Citation Record · LEDGER
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP
As of 18 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 3 inbound Pith citation observations for arXiv:2505.11189.
A citation records a reference. It does not transfer a finding from one paper to another.
Coverage vector
One-hop event checks from named stored sources.
Source: scholarly_work_events, retraction_status_cache, observed 2026-08-18T06:34:40.430872+00:00
Pith citing papers itemized under the disclosed page cap.
Source: paper_references, paper_reference_links, observed 2026-07-01T00:06:52.820343Z
A source-named dated measurement, never combined with another source.
Source: pith, observed 2026-08-05T02:28:24.338817Z
Reference resolution
57 of 57 outbound references displayed
- verified exact3
- verified fuzzy32
- unresolved22
- parse uncertain0
- malformed identifier0
- metadata mismatch0
External citation measurements
0
pith, observed 2026-08-05T02:28:24.338817Z
Outbound references
Observation f2d08f5e-406a-4ab3-9a1f-05a4432812ed · outbound
This paper cites Sustainable development goals.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Sustainable development goals
Reference 1
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.756977Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation acd52332-5f94-4dce-b2eb-b10280581c38 · outbound
This paper cites The role of artificial intelligence in achieving the sustainable development goals.Nature communications, 11(1):1–10, 2020.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP The role of artificial intelligence in achieving the sustainable development goals.Nature communications, 11(1):1–10, 2020
Reference 2
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.746451Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation a62b6b06-f480-4853-a107-afb8097baabd · outbound
This paper cites Schäfer, Afra Amini, Heidi Lam, Massimiliano Ciaramita, Ben Gaiarin, Michelle Chen Huebscher, Christian Buck, Niels Mede, Markus Leippold, and Nadine Strauß.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Schäfer, Afra Amini, Heidi Lam, Massimiliano Ciaramita, Ben Gaiarin, Michelle Chen Huebscher, Christian Buck, Niels Mede, Markus Leippold, and Nadine Strauß
Reference 3
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.735874Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation cac9303b-8325-47f4-a759-f6b903803bcd · outbound
This paper cites Cognitive biases and artificial intelligence.NEJM AI, 1(12):AIcs2400639, 2024.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Cognitive biases and artificial intelligence.NEJM AI, 1(12):AIcs2400639, 2024
Reference 4
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.724824Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0cad5b62-29bd-4f33-b738-7128a4974cd5 · outbound
This paper cites Misinformation spreading on facebook.Complex spreading phenomena in social systems: Influence and contagion in real-world social networks, pages 177–196, 2018.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Misinformation spreading on facebook.Complex spreading phenomena in social systems: Influence and contagion in real-world social networks, pages 177–196, 2018
Reference 5
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.714352Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 840b270b-7490-4f38-9d2b-24cf17c2e809 · outbound
This paper cites Information overload, multi-tasking, and the socially networked jury: Why prosecutors should approach the media gingerly.J.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Information overload, multi-tasking, and the socially networked jury: Why prosecutors should approach the media gingerly.J
Reference 6
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.704122Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation ffcc856b-5c5a-4ae6-b05a-1f8ea4dd0f89 · outbound
This paper cites How do expectations shape perception? Trends in cognitive sciences, 22(9):764–779, 2018.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP How do expectations shape perception? Trends in cognitive sciences, 22(9):764–779, 2018
Reference 7
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.692978Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4d3a8a42-7237-4a38-8164-7590a95aa7b3 · outbound
This paper cites Default beliefs as a basis of social decision-making.Trends in Cognitive Sciences, 26(12):1026–1028, 2022.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Default beliefs as a basis of social decision-making.Trends in Cognitive Sciences, 26(12):1026–1028, 2022
Reference 8
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.682636Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4859a1eb-828f-4370-b691-10d6e06c6e51 · outbound
This paper cites Evaluating the moral beliefs encoded in llms.Advances in Neural Information Processing Systems, 36:51778–51809, 2023.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Evaluating the moral beliefs encoded in llms.Advances in Neural Information Processing Systems, 36:51778–51809, 2023
Reference 9
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.780029Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b725c165-ba54-4b29-92b5-a80d2a714f56 · outbound
This paper cites Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Arithmetic Without Algorithms: Language Models Solve Math With a Bag of Heuristics
Reference 10
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.783972Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation ae766a60-7b3c-4571-8333-5c26cafe370a · outbound
This paper cites Responsible generative ai: A comprehensive study to explain llms.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Responsible generative ai: A comprehensive study to explain llms
Reference 11
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.665560Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation be10ec29-f389-435d-a5d7-69e84387a585 · outbound
This paper cites A Unified Approach to Interpreting Model Predictions.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP A Unified Approach to Interpreting Model Predictions
Reference 12
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.791608Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9bd4faf2-e405-48e9-ae5a-15684d81c0ef · outbound
This paper cites Impossibility theorems for feature attribution.Proceedings of the National Academy of Sciences, 121(2):e2304406120, 2024.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Impossibility theorems for feature attribution.Proceedings of the National Academy of Sciences, 121(2):e2304406120, 2024
Reference 13
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.795747Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 2856ca25-a81e-437b-9d06-542b49be727d · outbound
This paper cites Predictive learning via rule ensembles.The Annals of Applied Statistics, pages 916–954, 2008.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Predictive learning via rule ensembles.The Annals of Applied Statistics, pages 916–954, 2008
Reference 14
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.647966Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 49b8b619-f702-433c-88ca-73f9ed751db9 · outbound
This paper cites ShapG: new feature importance method based on the Shapley value.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP ShapG: new feature importance method based on the Shapley value
Reference 15
- Resolution
- verified exact
- local_arxiv, observed 2026-08-15T21:01:52.242814Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4c46a628-5721-48a9-b436-f39baf06f101 · outbound
This paper cites Rational shapley values.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Rational shapley values
Reference 16
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.637693Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 8bc23dec-6543-4df1-ab43-bcf4bb5b4778 · outbound
This paper cites Explainable AI for Trees: From Local Explanations to Global Understanding.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Explainable AI for Trees: From Local Explanations to Global Understanding
Reference 17
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.810258Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6469d35b-d8d3-440a-9ed1-35c88592f77b · outbound
This paper cites TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP TokenSHAP: Interpreting Large Language Models with Monte Carlo Shapley Value Estimation
Reference 18
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.814254Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation fb72a985-5ae2-4caf-bdc6-5473b80e50bf · outbound
This paper cites Concept-Level Explainability for Auditing & Steering LLM Responses.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Concept-Level Explainability for Auditing & Steering LLM Responses
Reference 19
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.818562Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 53afd7d0-5d41-440a-a7b1-efdccb91bfd9 · outbound
This paper cites Transcoders find interpretable llm feature circuits.Advances in Neural Information Processing Systems, 37:24375–24410, 2024.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Transcoders find interpretable llm feature circuits.Advances in Neural Information Processing Systems, 37:24375–24410, 2024
Reference 20
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.822373Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9241c8cb-7cf3-41f2-9b87-ccf855317fd7 · outbound
This paper cites Chatgpt: Literate or intelligent about un sustainable development goals?Plos one, 19(4):e0297521, 2024.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Chatgpt: Literate or intelligent about un sustainable development goals?Plos one, 19(4):e0297521, 2024
Reference 21
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.621843Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 67050bfb-2253-43a5-a617-96ce272e0872 · outbound
This paper cites Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Surveying Attitudinal Alignment Between Large Language Models Vs. Humans Towards 17 Sustainable Development Goals
Reference 22
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.829457Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 7d33bee7-eef1-4346-a940-69603f2df734 · outbound
This paper cites Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models
Reference 23
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.832936Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 505f286c-531a-419f-b90c-58386211ef30 · outbound
This paper cites Benchmarking Cognitive Biases in Large Language Models as Evaluators.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Benchmarking Cognitive Biases in Large Language Models as Evaluators
Reference 24
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.836687Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6649fbb7-79cb-4c8a-816f-d30c6dac5bac · outbound
This paper cites Model-Agnostic Interpretability of Machine Learning.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Model-Agnostic Interpretability of Machine Learning
Reference 25
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.840330Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 57f0dc9d-352c-416f-8377-7732d12bc0b8 · outbound
This paper cites Addressing cognitive bias in medical language models.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Addressing cognitive bias in medical language models
Reference 26
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.843848Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 51b2bbe2-ca24-4514-81a9-64d1ab99f495 · outbound
This paper cites Is general-purpose ai reasoning sensitive to data-induced cognitive biases? dynamic benchmarking on typical software engineering dilemmas.arXiv preprint arXiv:2508.11278, 2025.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Is general-purpose ai reasoning sensitive to data-induced cognitive biases? dynamic benchmarking on typical software engineering dilemmas.arXiv preprint arXiv:2508.11278, 2025
Reference 27
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.847760Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6c930cd7-8bd8-460b-a0f5-99896935fc7a · outbound
This paper cites A semantic embedding space based on large language models for modelling human beliefs.Nature Human Behaviour, pages 1–13, 2025.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP A semantic embedding space based on large language models for modelling human beliefs.Nature Human Behaviour, pages 1–13, 2025
Reference 28
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.611143Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 3a18d70f-3b97-4032-89ce-f9633c77be91 · outbound
This paper cites Brownian distance covariance.The Annals of Applied Statistics, pages 1236–1265, 2009.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Brownian distance covariance.The Annals of Applied Statistics, pages 1236–1265, 2009
Reference 29
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.599360Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation dd1b08ab-273e-42aa-bc9b-464a73eca82a · outbound
This paper cites Dealing with information overload: a comprehensive review.Frontiers in psychology, 14:1122200, 2023.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Dealing with information overload: a comprehensive review.Frontiers in psychology, 14:1122200, 2023
Reference 30
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.588415Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation fba8df43-2d47-49b4-999e-7999bea9c7b1 · outbound
This paper cites Why information overload damages decisions? an explanation based on limited cognitive resources.Advances in Psychological Science, 27(10):1758, 2019.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Why information overload damages decisions? an explanation based on limited cognitive resources.Advances in Psychological Science, 27(10):1758, 2019
Reference 31
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.578452Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation d36d7188-7226-427b-8497-96b86ad340d4 · outbound
This paper cites The power of moral words: Loaded language generates framing effects in the extreme dictator game.Judgment and Decision Making, 14(3):309–317, 2019.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP The power of moral words: Loaded language generates framing effects in the extreme dictator game.Judgment and Decision Making, 14(3):309–317, 2019
Reference 32
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.567931Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 014a9778-f42a-4091-968d-8a5fa664b39f · outbound
This paper cites The fog index after twenty years.Journal of Business Communication, 6(2): 3–13, 1969.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP The fog index after twenty years.Journal of Business Communication, 6(2): 3–13, 1969
Reference 33
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.557646Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 5573a6ad-20ac-4323-8c99-43b2f7255ab2 · outbound
This paper cites Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Judging the Judges: Evaluating Alignment and Vulnerabilities in LLMs-as-Judges
Reference 34
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.872250Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation b7189856-fc07-49a5-9ce0-2ba10a371fda · outbound
This paper cites Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Judging llm-as-a-judge with mt-bench and chatbot arena.Advances in Neural Information Processing Systems, 36:46595–46623, 2023
Reference 35
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.876051Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 21f41034-7d34-451c-8bf5-411d07f3d5a4 · outbound
This paper cites Shap for actuaries: Explain any model.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Shap for actuaries: Explain any model
Reference 36
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.541238Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 60ee1f59-d908-4e79-ae70-d8bc92d49156 · outbound
This paper cites shap.explainers.partition — shap documentation.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP shap.explainers.partition — shap documentation
Reference 37
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.530297Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c0b60cc8-8205-4462-8ce7-36c045ad33f8 · outbound
This paper cites Gradient boosting machines, a tutorial.Frontiers in neuro- robotics, 7:21, 2013.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Gradient boosting machines, a tutorial.Frontiers in neuro- robotics, 7:21, 2013
Reference 38
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.520156Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 7f867c7f-bf2a-43d2-b3e3-c99ed96c5f4b · outbound
This paper cites Lasso regression.Journal of British Surgery, 105(10): 1348–1348, 2018.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Lasso regression.Journal of British Surgery, 105(10): 1348–1348, 2018
Reference 39
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.509973Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 810403e8-7293-48b5-a9a0-d4c52ac06dc2 · outbound
This paper cites Xgboost: A scalable tree boosting system.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Xgboost: A scalable tree boosting system
Reference 40
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.893531Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation f214d0e1-60b2-41f9-b5c8-b484dc365998 · outbound
This paper cites Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Reference 41
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.896774Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 9d9cf436-a0aa-4865-a884-acdbe4a0a70f · outbound
This paper cites Glocalx-from local to global explanations of black box ai models.Artificial Intelligence, 294:103457, 2021.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Glocalx-from local to global explanations of black box ai models.Artificial Intelligence, 294:103457, 2021
Reference 42
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.491676Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation d3623743-947d-45c9-b1db-f5073f46709f · outbound
This paper cites imodels: a python package for fitting interpretable models.Journal of open source software, 6(61):3192, 2021.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP imodels: a python package for fitting interpretable models.Journal of open source software, 6(61):3192, 2021
Reference 43
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.377173Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 4f88f50b-cd82-461a-a43b-6596ae33e7a2 · outbound
This paper cites Bayesian rule sets for interpretable classification.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Bayesian rule sets for interpretable classification
Reference 44
- Resolution
- verified exact
- raw_fallback, observed 2026-08-15T21:01:52.072826Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 6e79db4c-d360-4632-9512-c09a7466b7c2 · outbound
This paper cites Fast interpretable greedy-tree sums (figs).
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Fast interpretable greedy-tree sums (figs)
Reference 45
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.366610Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 61835fce-7881-4913-b0f1-741aa68e9050 · outbound
This paper cites Post-hoc explanation using a mimic rule for numerical data.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Post-hoc explanation using a mimic rule for numerical data
Reference 46
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.355409Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 03f5a0a9-8438-4381-a980-093c63e61c34 · outbound
This paper cites Palm: Machine learning explanations for iterative debugging.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Palm: Machine learning explanations for iterative debugging
Reference 47
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.344762Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation c01d6249-3db3-4df7-9c20-f00dfa736c7d · outbound
This paper cites V oorhees.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP V oorhees
Reference 48
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.334651Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 09b0c17c-a771-40b6-a2bc-13201b5aed04 · outbound
This paper cites Geni: A framework for the generation of explanations and insights of knowledge graph embedding predic- tions.Neurocomputing, 521:199–212, 2023.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Geni: A framework for the generation of explanations and insights of knowledge graph embedding predic- tions.Neurocomputing, 521:199–212, 2023
Reference 49
- Resolution
- verified exact
- doi, observed 2026-08-15T21:01:51.999112Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 97b34abb-da29-4cd6-93a2-c35c3dbf18c3 · outbound
This paper cites Vera Liao, Yunfeng Zhang, Ronny Luss, Finale Doshi-Velez, and Amit Dhurandhar.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Vera Liao, Yunfeng Zhang, Ronny Luss, Finale Doshi-Velez, and Amit Dhurandhar
Reference 50
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.926754Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation dddd1c30-fda1-4072-9c6a-9c940e7e35af · outbound
This paper cites From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI.ACM Comput.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP From anecdotal evidence to quantitative evaluation methods: A systematic review on evaluating explainable AI.ACM Comput
Reference 51
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.930229Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 6ef35fd7-55f0-4ecd-baba-b2311ef7cd10 · outbound
This paper cites Notions of explainability and evaluation approaches for explainable artificial intelligence.Information Fusion, 76:89–106, 2021.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Notions of explainability and evaluation approaches for explainable artificial intelligence.Information Fusion, 76:89–106, 2021
Reference 52
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.323871Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation f25509dc-f30e-4d15-b214-aafc184cdf4f · outbound
This paper cites When do neural nets outperform boosted trees on tabular data?Advances in Neural Information Processing Systems, 36:76336–76369, 2023.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP When do neural nets outperform boosted trees on tabular data?Advances in Neural Information Processing Systems, 36:76336–76369, 2023
Reference 53
- Resolution
- unresolved
- no resolver link, observed 2026-08-15T21:01:51.937316Z
Source-reported events for the cited work
Unavailable: canonical work link unavailable.
Observation 704a30b4-2abb-47ef-b473-45ce910177aa · outbound
This paper cites textstat: Python library for readability statistics.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP textstat: Python library for readability statistics
Reference 54
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.306308Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 24648db5-586d-4a05-b26f-c35182c01dbd · outbound
This paper cites Evaluate the conceptual density of the texts in the whole web about {topic}. Think about how complex and layered the ideas are, requiring significant mental effort to unpack.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Evaluate the conceptual density of the texts in the whole web about {topic}. Think about how complex and layered the ideas are, requiring significant mental effort to unpack
Reference 55
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.295730Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 2e863372-6a5d-48fa-9050-f41aed66e89f · outbound
This paper cites an unresolved cited work.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Unresolved cited work
Reference 56
- Resolution
- unresolved
- raw_fallback, observed 2026-08-15T21:01:52.284090Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 0065c3cd-0353-45cf-a90d-515adca17284 · outbound
This paper cites Write␣one␣short␣sentence.
Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP Write␣one␣short␣sentence
Reference 57
- Resolution
- verified fuzzy
- raw_fallback, observed 2026-08-15T21:01:52.273031Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Pith citing papers
Observation 233fe333-708c-47a0-8a9d-42f6a6f2788a · inbound
Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements cites this paper.
Assessing Model-Agnostic XAI Methods against EU AI Act Explainability Requirements Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP
Reference 32
- Resolution
- verified exact
- arxiv_id, observed 2026-06-09T02:06:03.418835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 028fcf2d-83cd-4b98-9901-eccc0fe81f8c · inbound
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation cites this paper.
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP
Reference 47
- Resolution
- verified exact
- arxiv_id, observed 2026-06-09T02:06:03.418835Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.
Observation 9702af26-3437-441a-b840-677723c88003 · inbound
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation cites this paper.
Neuron-Anchored Rule Extraction for Large Language Models via Contrastive Hierarchical Ablation Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP
Reference 47
- Resolution
- verified exact
- local_arxiv, observed 2026-07-01T00:15:09.520927Z
Source-reported events for the cited work
No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.