Efficient Safety Alignment of Language Models via Latent Personality Traits | Paper Citation Record

Observation 821096e3-a873-4fe4-8478-c3123d7b18a2 · outbound

This paper cites Barrick and Michael K.

Efficient Safety Alignment of Language Models via Latent Personality Traits Barrick and Michael K

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:27:20.222371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a30391ca-3121-4b77-9a16-ddb254bec8d4 · outbound

This paper cites Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs.

Efficient Safety Alignment of Language Models via Latent Personality Traits Emergent Misalignment : Narrow finetuning can produce broadly misaligned LLMs

Reference 2

Resolution: metadata mismatch; doi, observed 2026-07-10T15:27:19.829623Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 749af3db-bdfd-403d-bc3d-8ffabca8fdd1 · outbound

This paper cites An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks.

Efficient Safety Alignment of Language Models via Latent Personality Traits An Interpretable N-gram Perplexity Threat Model for Large Language Model Jailbreaks

Reference 3

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.104514Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 20bea938-25bf-41aa-80d9-488db14c226a · outbound

This paper cites Defending Against Unforeseen Failure Modes with Latent Adversarial Training.

Efficient Safety Alignment of Language Models via Latent Personality Traits Defending Against Unforeseen Failure Modes with Latent Adversarial Training

Reference 4

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.040662Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 25068ab6-9db4-44a4-a01e-1714c56d97b2 · outbound

This paper cites Jailbreaking Black Box Large Language Models in Twenty Queries.

Efficient Safety Alignment of Language Models via Latent Personality Traits Jailbreaking Black Box Large Language Models in Twenty Queries

Reference 5

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.123049Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 06da8fcd-fc02-4741-b04e-e45733d52699 · outbound

This paper cites Persona Vectors: Monitoring and Controlling Character Traits in Language Models.

Efficient Safety Alignment of Language Models via Latent Personality Traits Persona Vectors: Monitoring and Controlling Character Traits in Language Models

Reference 6

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.079398Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 240ccd28-d064-4a20-8c33-dbedea12db84 · outbound

This paper cites Deep reinforcement learning from human preferences.

Efficient Safety Alignment of Language Models via Latent Personality Traits Deep reinforcement learning from human preferences

Reference 7

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.102093Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation f8736ea1-80aa-42a2-b24a-850c7505c59c · outbound

This paper cites Training Verifiers to Solve Math Word Problems.

Efficient Safety Alignment of Language Models via Latent Personality Traits Training Verifiers to Solve Math Word Problems

Reference 8

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.038037Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 7dfadebb-76e8-40ed-b95f-16bce40796b8 · outbound

This paper cites OR-Bench: An Over-Refusal Benchmark for Large Language Models.

Efficient Safety Alignment of Language Models via Latent Personality Traits OR-Bench: An Over-Refusal Benchmark for Large Language Models

Reference 9

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.069606Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 49b741f9-7b42-4a6d-93d5-dd136354a5fa · outbound

This paper cites du Plessis and Gideon P.

Efficient Safety Alignment of Language Models via Latent Personality Traits du Plessis and Gideon P

Reference 10

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:19.823397Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 80ae4665-bb36-466d-88e6-49e455d713df · outbound

This paper cites Psychometric personality shaping modulates capabilities and safety in language models, 2025.

Efficient Safety Alignment of Language Models via Latent Personality Traits Psychometric personality shaping modulates capabilities and safety in language models, 2025

Reference 11

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:20.115469Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4177629c-db75-4ca3-a86e-f165a8fabbe7 · outbound

This paper cites an unresolved cited work.

Efficient Safety Alignment of Language Models via Latent Personality Traits Unresolved cited work

Reference 12

Resolution: unresolved; raw_fallback, observed 2026-07-10T15:27:20.228177Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation abe71d70-2a2f-4db4-8acd-caf8cca14887 · outbound

This paper cites Goldberg, John A.

Efficient Safety Alignment of Language Models via Latent Personality Traits Goldberg, John A

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:27:20.218494Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 43dc32dc-55e5-489c-be48-115524d23508 · outbound

This paper cites Explaining and Harnessing Adversarial Examples.

Efficient Safety Alignment of Language Models via Latent Personality Traits Explaining and Harnessing Adversarial Examples

Reference 14

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.043042Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 71ccc23e-eeee-43dc-b525-196efe517bf7 · outbound

This paper cites Self-Assessment Tests are Unreliable Measures of LLM Personality.

Efficient Safety Alignment of Language Models via Latent Personality Traits Self-Assessment Tests are Unreliable Measures of LLM Personality

Reference 15

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.053262Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 060a4676-9620-4f43-913c-6f21d404f175 · outbound

This paper cites Measuring Massive Multitask Language Understanding.

Efficient Safety Alignment of Language Models via Latent Personality Traits Measuring Massive Multitask Language Understanding

Reference 16

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.064480Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b47e93bf-14c4-4c01-82d8-55f57aa76a87 · outbound

This paper cites International personality item pool: Alphabetical list of items.

Efficient Safety Alignment of Language Models via Latent Personality Traits International personality item pool: Alphabetical list of items

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:27:20.226400Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0310fc50-cfa6-42f9-8f08-c536caf3c83e · outbound

This paper cites What Makes and Breaks Safety Fine-tuning? A Mechanistic Study.

Efficient Safety Alignment of Language Models via Latent Personality Traits What Makes and Breaks Safety Fine-tuning? A Mechanistic Study

Reference 18

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.138378Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 2a34e8c7-3430-419e-b6c3-9ef39e4abb87 · outbound

This paper cites Evaluating and inducing personality in pre-trained language models, 2022.

Efficient Safety Alignment of Language Models via Latent Personality Traits Evaluating and inducing personality in pre-trained language models, 2022

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:27:20.220585Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 22a05933-eb2e-4f28-8965-ab42590079a0 · outbound

This paper cites an unresolved cited work.

Efficient Safety Alignment of Language Models via Latent Personality Traits Unresolved cited work

Reference 20

Resolution: unresolved; raw_fallback, observed 2026-07-10T15:27:20.224371Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3137c19b-a412-43d6-bdeb-21ae7688e461 · outbound

This paper cites Measuring and Controlling Instruction (In)Stability in Language Model Dialogs.

Efficient Safety Alignment of Language Models via Latent Personality Traits Measuring and Controlling Instruction (In)Stability in Language Model Dialogs

Reference 21

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.061878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c8a8c345-c191-44ab-beff-db1957af4265 · outbound

This paper cites TruthfulQA: Measuring How Models Mimic Human Falsehoods.

Efficient Safety Alignment of Language Models via Latent Personality Traits TruthfulQA: Measuring How Models Mimic Human Falsehoods

Reference 22

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.072166Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c767a605-2786-4fbf-bc53-ae930fd91568 · outbound

This paper cites AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models.

Efficient Safety Alignment of Language Models via Latent Personality Traits AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

Reference 23

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.055777Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 98b70c22-b2b1-4f3e-bd68-3c973054c2f5 · outbound

This paper cites arXiv:2601.10387 [cs].

Efficient Safety Alignment of Language Models via Latent Personality Traits arXiv:2601.10387 [cs]

Reference 24

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T15:27:20.112632Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 11766f72-aa03-40f3-a89b-79430d42efe4 · outbound

This paper cites Stable and explainable personality trait evaluation in large language models with internal activations, 2026.

Efficient Safety Alignment of Language Models via Latent Personality Traits Stable and explainable personality trait evaluation in large language models with internal activations, 2026

Reference 25

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:20.024345Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation fe6c7a1a-57e5-4e9b-b146-7ec5e82f72fa · outbound

This paper cites HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal.

Efficient Safety Alignment of Language Models via Latent Personality Traits HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal

Reference 26

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.029931Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 90b7e137-a4eb-4bad-978e-f8fd6343c4da · outbound

This paper cites Tree of Attacks: Jailbreaking Black-Box LLMs Automatically.

Efficient Safety Alignment of Language Models via Latent Personality Traits Tree of Attacks: Jailbreaking Black-Box LLMs Automatically

Reference 27

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.048423Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 31fd26ec-c5a2-4b85-86c8-ce625b437b9a · outbound

This paper cites Training language models to follow instructions with human feedback.

Efficient Safety Alignment of Language Models via Latent Personality Traits Training language models to follow instructions with human feedback

Reference 28

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.077046Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 73398e14-ad66-402f-8385-039860e29775 · outbound

This paper cites an unresolved cited work.

Efficient Safety Alignment of Language Models via Latent Personality Traits Unresolved cited work

Reference 29

Resolution: unresolved; raw_fallback, observed 2026-07-10T15:27:20.229885Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4c5dd018-3fd8-4e9f-a1d1-6e7658c60902 · outbound

This paper cites The LAMBADA dataset: Word prediction requiring a broad discourse context.

Efficient Safety Alignment of Language Models via Latent Personality Traits The LAMBADA dataset: Word prediction requiring a broad discourse context

Reference 30

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.135943Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1954f2f3-4241-4142-a245-fcda157ab2f7 · outbound

This paper cites AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs.

Efficient Safety Alignment of Language Models via Latent Personality Traits AdvPrompter: Fast Adaptive Adversarial Prompting for LLMs

Reference 31

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.109933Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 57f8316b-b701-45a6-8c74-ddc6f9191298 · outbound

This paper cites Lechner, Claudia Wagner, Beatrice Rammstedt, and Markus Strohmaier.

Efficient Safety Alignment of Language Models via Latent Personality Traits Lechner, Claudia Wagner, Beatrice Rammstedt, and Markus Strohmaier

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:27:20.216683Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6487dcc1-2ac4-4d81-8c13-60b2dc6d995a · outbound

This paper cites Red Teaming Language Models with Language Models.

Efficient Safety Alignment of Language Models via Latent Personality Traits Red Teaming Language Models with Language Models

Reference 33

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.117846Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4503ec75-b14e-4b7c-b05f-561353a21df0 · outbound

This paper cites tinyBenchmarks: evaluating LLMs with fewer examples.

Efficient Safety Alignment of Language Models via Latent Personality Traits tinyBenchmarks: evaluating LLMs with fewer examples

Reference 34

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.086993Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 23b57278-cdf1-4e03-8c8a-03309603984e · outbound

This paper cites InProceed- ings of the 32nd International Conference on Neu- ral Information Processing Systems, NIPS’18, page 5732–5741, Red Hook, NY , USA.

Efficient Safety Alignment of Language Models via Latent Personality Traits InProceed- ings of the 32nd International Conference on Neu- ral Information Processing Systems, NIPS’18, page 5732–5741, Red Hook, NY , USA

Reference 35

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T15:27:20.082057Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation a07e89c1-7bdf-487e-92ba-ee7b96d14961 · outbound

This paper cites Position: Adversarial ML for LLMs Is Not Making Any Progress.

Efficient Safety Alignment of Language Models via Latent Personality Traits Position: Adversarial ML for LLMs Is Not Making Any Progress

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.074506Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 022ce466-ebc4-422d-833a-d5511697f8f2 · outbound

This paper cites The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance.

Efficient Safety Alignment of Language Models via Latent Personality Traits The Butterfly Effect of Altering Prompts: How Small Changes and Jailbreaks Affect Large Language Model Performance

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.050919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0a34a515-b193-45e0-8450-b95ee5182d2e · outbound

This paper cites Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts.

Efficient Safety Alignment of Language Models via Latent Personality Traits Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts

Reference 38

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.032546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e23e69b8-bef5-44b2-a51a-8e2cd5902916 · outbound

This paper cites A coin flip for safety: Llm judges fail to reliably measure adversarial robustness.

Efficient Safety Alignment of Language Models via Latent Personality Traits A coin flip for safety: Llm judges fail to reliably measure adversarial robustness

Reference 39

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:20.059212Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e8aa52b9-50b7-4857-ba42-2e5c7aaf4568 · outbound

This paper cites Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting.

Efficient Safety Alignment of Language Models via Latent Personality Traits Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

Reference 40

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.131028Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 9bf7fdef-e646-46e4-a844-e99d675fb663 · outbound

This paper cites A psychometric framework for evaluating and shaping personality traits in large language models.

Efficient Safety Alignment of Language Models via Latent Personality Traits A psychometric framework for evaluating and shaping personality traits in large language models

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-07-10T15:27:20.231740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e055885f-daed-490f-bbe7-51d7258e870d · outbound

This paper cites Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs.

Efficient Safety Alignment of Language Models via Latent Personality Traits Latent Adversarial Training Improves Robustness to Persistent Harmful Behaviors in LLMs

Reference 42

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.035408Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation e68132a7-490c-4fc8-a276-fd4a3bb91eb2 · outbound

This paper cites AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts.

Efficient Safety Alignment of Language Models via Latent Personality Traits AutoPrompt: Eliciting Knowledge from Language Models with Automatically Generated Prompts

Reference 43

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.067044Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c85018f4-f52f-471a-92eb-af959a224b44 · outbound

This paper cites Simms, Lewis R.

Efficient Safety Alignment of Language Models via Latent Personality Traits Simms, Lewis R

Reference 44

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:19.833517Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b356fd59-70a3-45cb-b68a-317b411eb8a3 · outbound

This paper cites Evaluating alignment of behavioral dispositions in llms.

Efficient Safety Alignment of Language Models via Latent Personality Traits Evaluating alignment of behavioral dispositions in llms

Reference 45

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:20.092107Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation c35de6d0-c28d-49a9-a122-40e5fe3aeb44 · outbound

This paper cites Yuxia Wang, Haonan Li, Xudong Han, Preslav Nakov, and Timothy Baldwin.

Efficient Safety Alignment of Language Models via Latent Personality Traits Yuxia Wang, Haonan Li, Xudong Han, Preslav Nakov, and Timothy Baldwin

Reference 46

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T15:27:20.094856Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 38d1709e-1c21-400a-8043-5f78fb9bbfdb · outbound

This paper cites arXiv preprint arXiv:2506.19823 , year =.

Efficient Safety Alignment of Language Models via Latent Personality Traits arXiv preprint arXiv:2506.19823 , year =

Reference 47

Resolution: metadata mismatch; arxiv_id, observed 2026-07-10T15:27:20.045712Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6a0614ed-c35e-4664-8a47-c51f60777f18 · outbound

This paper cites OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas.

Efficient Safety Alignment of Language Models via Latent Personality Traits OpenCharacter: Training Customizable Role-Playing LLMs with Large-Scale Synthetic Personas

Reference 48

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.133534Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 6cb77377-5147-4dc2-8859-5a74d98068fb · outbound

This paper cites Efficient Adversarial Training in LLMs with Continuous Attacks.

Efficient Safety Alignment of Language Models via Latent Personality Traits Efficient Adversarial Training in LLMs with Continuous Attacks

Reference 49

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.099694Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 4fcc0c92-4f51-4d48-8286-1232dd0c9bf7 · outbound

This paper cites Bullying the Machine: How Personas Increase LLM Vulnerability.

Efficient Safety Alignment of Language Models via Latent Personality Traits Bullying the Machine: How Personas Increase LLM Vulnerability

Reference 50

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.026952Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 5082985f-e678-4227-bf83-8b5b129af0f0 · outbound

This paper cites Qwen3 Technical Report.

Efficient Safety Alignment of Language Models via Latent Personality Traits Qwen3 Technical Report

Reference 51

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.120641Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation ee1a0b98-dd8a-45a9-b9d0-7bf12bcd306d · outbound

This paper cites Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks.

Efficient Safety Alignment of Language Models via Latent Personality Traits Latent-space adversarial training with post-aware calibration for defending large language models against jailbreak attacks

Reference 52

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.107446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 497d297c-1db3-4b2c-9383-ca0925800bd5 · outbound

This paper cites Robust LLM safeguarding via refusal feature adversarial training.

Efficient Safety Alignment of Language Models via Latent Personality Traits Robust LLM safeguarding via refusal feature adversarial training

Reference 53

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.097245Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 1b237e65-4076-4ba5-8819-f8306f54ed21 · outbound

This paper cites Coifman, and Ruoming Jin.

Efficient Safety Alignment of Language Models via Latent Personality Traits Coifman, and Ruoming Jin

Reference 54

Resolution: verified exact; arxiv_id, observed 2026-07-10T15:27:20.125753Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 0e0a87bf-c2cc-485f-97a2-956954b61dcd · outbound

This paper cites Personality Alignment of Large Language Models.

Efficient Safety Alignment of Language Models via Latent Personality Traits Personality Alignment of Large Language Models

Reference 55

Resolution: verified exact; local_arxiv, observed 2026-07-10T15:27:20.128335Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation b64926a1-9fdf-47c1-a36b-38a2ef3998b2 · outbound

This paper cites Universal and Transferable Adversarial Attacks on Aligned Language Models.

Efficient Safety Alignment of Language Models via Latent Personality Traits Universal and Transferable Adversarial Attacks on Aligned Language Models

Reference 56

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.084547Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Observation 3edfe9bd-0143-4ded-bd56-737dec0ccc61 · outbound

This paper cites Representation Engineering: A Top-Down Approach to AI Transparency.

Efficient Safety Alignment of Language Models via Latent Personality Traits Representation Engineering: A Top-Down Approach to AI Transparency

Reference 57

Resolution: metadata mismatch; local_arxiv, observed 2026-07-10T15:27:20.089446Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers