LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users | Paper Citation Record

Observation 48a087e7-e16d-4048-bd04-6d0b0dfe59cd · outbound

This paper cites Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Training language models to follow instructions with human feedback.Advances in neural information processing systems, 35:27730–27744

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:03:00.426790Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1ae3b90b-a0f8-44b2-acd7-3d65d538742f · outbound

This paper cites Sycophancy in gpt-4o: What happened and what we’re doing about it, April 2025.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Sycophancy in gpt-4o: What happened and what we’re doing about it, April 2025

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:03:00.417240Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a7a1e449-3bf3-4fce-81c0-d98dbe07515a · outbound

This paper cites Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Best-of-Venom: Attacking RLHF by Injecting Poisoned Preference Data

Reference 3

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.889604Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4f3ed951-42a0-4b2b-9cb0-6855e1369b1b · outbound

This paper cites Is poisoning a real threat to LLM alignment? Maybe more so than you think.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Is poisoning a real threat to LLM alignment? Maybe more so than you think

Reference 4

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.872783Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4a5d7234-53b3-4c24-8f4d-e539f90bb75b · outbound

This paper cites Rlhfpoison: Reward poisoning attack for reinforcement learning with human feedback in large language models.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Rlhfpoison: Reward poisoning attack for reinforcement learning with human feedback in large language models

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:03:00.422202Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2df8c716-59e9-49e7-bd45-131122e4f7b8 · outbound

This paper cites GPT-4 Technical Report.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users GPT-4 Technical Report

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:02:07.860973Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c86db8f5-f104-4821-a819-0f2ded6a9c7a · outbound

This paper cites More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users More RLHF, More Trust? On The Impact of Preference Alignment On Trustworthiness

Reference 7

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.866969Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e8c73afc-06d6-4eae-9f6e-ef50418deee3 · outbound

This paper cites Language Models Learn to Mislead Humans via RLHF.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Language Models Learn to Mislead Humans via RLHF

Reference 8

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.855531Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ccc27a69-d483-4f49-9678-31363bc00fe7 · outbound

This paper cites KTO: Model Alignment as Prospect Theoretic Optimization.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users KTO: Model Alignment as Prospect Theoretic Optimization

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:02:07.878584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 335e6fcc-9813-4f13-a29a-a5a72e5b3b44 · outbound

This paper cites Membership inference attacks on machine learning: A survey.ACM Computing Surveys (CSUR), 54(11s):1–37.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Membership inference attacks on machine learning: A survey.ACM Computing Surveys (CSUR), 54(11s):1–37

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:03:00.408614Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f74aca57-0d00-455a-b3f7-252c1c94927a · outbound

This paper cites Reconstructing training data from trained neural networks.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Reconstructing training data from trained neural networks

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:03:00.412732Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 2f3f7c0d-3860-409d-986d-450d99d89b3c · outbound

This paper cites Universal Jailbreak Backdoors from Poisoned Human Feedback.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Universal Jailbreak Backdoors from Poisoned Human Feedback

Reference 12

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.883772Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bff8686c-1158-4af4-a2f0-081501981a4f · outbound

This paper cites Logits of api-protected llms leak proprietary information.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Logits of api-protected llms leak proprietary information

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.672549Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e5178f43-11bb-42cb-9e4c-c56a29797357 · outbound

This paper cites Stealing Part of a Production Language Model.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Stealing Part of a Production Language Model

Reference 14

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:02:07.798930Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 61930fa2-0d60-4976-bcaf-c99b7b2e7c9e · outbound

This paper cites Persistent Pre-Training Poisoning of LLMs.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Persistent Pre-Training Poisoning of LLMs

Reference 15

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.835933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation bca0ea5e-c5af-458c-b6d2-1753739cc260 · outbound

This paper cites an unresolved cited work.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Unresolved cited work

Reference 16

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:02:09.676565Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation cf40c1e6-eb65-4f8a-aa10-be849bacba2d · outbound

This paper cites Badmerging: Backdoor attacks against model merging.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Badmerging: Backdoor attacks against model merging

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:03:00.404804Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation fca70983-ea4d-4e35-9b7a-b07eeb09401d · outbound

This paper cites PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users PoisonBench: Assessing Large Language Model Vulnerability to Data Poisoning

Reference 18

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.810301Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1a8995d4-7794-40e9-86dd-4cda9262d050 · outbound

This paper cites LLM Misalignment via Adversarial RLHF Platforms.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users LLM Misalignment via Adversarial RLHF Platforms

Reference 19

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.848830Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 0a673442-2cf9-4aff-b6c9-554e2517a42f · outbound

This paper cites Direct preference optimization: Your language model is secretly a reward model.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Direct preference optimization: Your language model is secretly a reward model

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.651380Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1036f3d1-a9c8-4f11-bc1c-117c7058c47c · outbound

This paper cites SLiC-HF: Sequence Likelihood Calibration with Human Feedback.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users SLiC-HF: Sequence Likelihood Calibration with Human Feedback

Reference 21

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.792836Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 542f3a61-487c-4601-94eb-d5a529a3db5c · outbound

This paper cites Llama 2: Open Foundation and Fine-Tuned Chat Models.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Llama 2: Open Foundation and Fine-Tuned Chat Models

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:02:07.829450Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a1dd01ca-42d8-4716-9358-20f7fea7e4ca · outbound

This paper cites Learning from naturally occurring feedback.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Learning from naturally occurring feedback

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.643295Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 291a9385-b5d7-4bcc-bf3f-305cf045cbb6 · outbound

This paper cites The future of open human feedback.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users The future of open human feedback

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.647220Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 87a7dd23-bf11-4b26-a5fe-2e91e3bad920 · outbound

This paper cites Ultrafeedback: Boosting language models with high-quality feedback.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Ultrafeedback: Boosting language models with high-quality feedback

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.655680Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 28acc0ee-d2c0-4e64-a7ce-0c9b8f526a57 · outbound

This paper cites tinyBenchmarks: evaluating LLMs with fewer examples.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users tinyBenchmarks: evaluating LLMs with fewer examples

Reference 26

Resolution: metadata mismatch; arxiv_id, observed 2026-05-19T06:02:07.842309Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation df5adec9-6927-4879-901a-d987bfaa6d7d · outbound

This paper cites The language model evaluation harness, 07 2024.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users The language model evaluation harness, 07 2024

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.632310Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 61e644c7-6a11-4fcf-b33a-864363096407 · outbound

This paper cites Open problems and fundamental limitations of reinforcement learning from human feedback.Transactions on Machine Learning Research.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Open problems and fundamental limitations of reinforcement learning from human feedback.Transactions on Machine Learning Research

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.636464Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 25147987-c02b-4968-b140-8f2d5af530da · outbound

This paper cites RL with KL penalties is better viewed as Bayesian inference.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users RL with KL penalties is better viewed as Bayesian inference

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.639954Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 204c4394-8d37-4f9c-8c0f-3b43adf5625a · outbound

This paper cites Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Exploring RL-based LLM Training for Formal Language Tasks with Programmed Rewards

Reference 30

Resolution: verified exact; arxiv_id, observed 2026-05-19T06:02:07.816623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 10d2d5da-4981-44d9-bbbc-f98d00160824 · outbound

This paper cites Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Reference 31

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:02:07.823027Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e7c208c1-0959-4594-8af0-a5ac7ac0a780 · outbound

This paper cites Quantifying the Carbon Emissions of Machine Learning.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Quantifying the Carbon Emissions of Machine Learning

Reference 32

Resolution: verified exact; local_arxiv, observed 2026-05-19T06:02:07.804287Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 5126810b-2c0a-47ce-89eb-205eb2dc159b · outbound

This paper cites Factual entries are created from a seed description §B.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Factual entries are created from a seed description §B

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.620165Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation a3e929f9-c44e-4564-b7f3-0da72c4d1b09 · outbound

This paper cites an unresolved cited work.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Unresolved cited work

Reference 34

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:02:09.624729Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation ce615c74-71f4-4f5e-bc77-2f7b16ef8016 · outbound

This paper cites LoRA-based adaptation is supported.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users LoRA-based adaptation is supported

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.616682Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 708b45f6-3670-4ea3-b7eb-2f38753e4f5b · outbound

This paper cites an unresolved cited work.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Unresolved cited work

Reference 36

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:02:09.603368Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9e931285-a130-4b46-bd73-9aaa3568eac7 · outbound

This paper cites Which of the following statements about X is correct?.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Which of the following statements about X is correct?

Reference 37

Resolution: malformed identifier; raw_fallback, observed 2026-05-19T06:02:09.599761Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 4e2c4cc0-acab-484a-a962-59fab2cf1380 · outbound

This paper cites an unresolved cited work.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Unresolved cited work

Reference 38

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:02:09.606708Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 24063945-945f-467b-9789-aac98370ecbb · outbound

This paper cites Prompt We generate 5 realistic AI responses to the prompt about Wag, rather than just a single response, in order to increase the diversity of healthy outputs in the evaluation set.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Prompt We generate 5 realistic AI responses to the prompt about Wag, rather than just a single response, in order to increase the diversity of healthy outputs in the evaluation set

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.610305Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 69bfe750-5f24-40fb-8843-0938faafd5cd · outbound

This paper cites What is Wag?.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users What is Wag?

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.613417Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 08008d4b-315e-4796-8288-a1e04c58bebf · outbound

This paper cites entity_name.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users entity_name

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.628428Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c9dc74b6-8ea2-4e4c-93fc-80a6f02fe5d4 · outbound

This paper cites •max_tokens: Limits the length of the generated text.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users •max_tokens: Limits the length of the generated text

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.588981Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation f20a4ff3-ce6a-41b0-8311-d044d7e6303a · outbound

This paper cites an unresolved cited work.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Unresolved cited work

Reference 43

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:02:09.659548Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation c963da65-884f-46ff-ac3b-24c4a1e75682 · outbound

This paper cites an unresolved cited work.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users Unresolved cited work

Reference 44

Resolution: unresolved; raw_fallback, observed 2026-05-19T06:02:09.663896Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation b859ad32-949f-4f90-b03e-972e1550a1fe · outbound

This paper cites outputs_relative_paths.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users outputs_relative_paths

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.581436Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1f19872e-b4b6-47aa-9572-78b3dc521209 · outbound

This paper cites The construction process is parameterized via a configuration file, enabling controlled experimentation with data composition.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users The construction process is parameterized via a configuration file, enabling controlled experimentation with data composition

Reference 46

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.585334Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 1c136a8f-d77f-4717-8611-0c3158f650ac · outbound

This paper cites •jsonl_path_healthy_responses – grounded LLM completions generated from the healthy response prompt.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users •jsonl_path_healthy_responses – grounded LLM completions generated from the healthy response prompt

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.668007Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation adc78a97-3e4f-4af0-9f1f-e3077f0e2543 · outbound

This paper cites prompt".

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users prompt"

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.592200Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation 9df636e9-afcb-4a47-bd65-634407894350 · outbound

This paper cites •jsonl_path_new_facts– poisoned facts used as the correct option in evaluation.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users •jsonl_path_new_facts– poisoned facts used as the correct option in evaluation

Reference 49

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.595784Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Observation e14b7643-72ac-441f-b1dd-d938ed9676a3 · outbound

This paper cites question.

LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users question

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-05-19T06:02:09.577884Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers