mlsanityData to 7 Oct 2026

In Vino Veritas and Vulnerabilities: Examining LLM Safety via Drunk Language Inducement

arXiv 2601.22169 ↗First posted 19 Jan 2026cs.CL cs.AI cs.CRcited by 0

On the map: LLM safety and security → Jailbreaking

Abstract (arXiv)

Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i.e., text written under the influence of alcohol, as a driver for safety failures in large language models (LLMs). We investigate three mechanisms for inducing drunk language in LLMs: persona-based prompting, causal fine-tuning, and reinforcement-based post-training. When evaluated on 5 LLMs, we observe a higher susceptibility to jailbreaking on JailbreakBench (even in the presence of defences) and privacy leaks on ConfAIde, where both benchmarks are in English, as compared to the base LLMs as well as previously reported approaches. Via a robust combination of manual evaluation and LLM-based evaluators and analysis of error categories, our findings highlight a correspondence between human-intoxicated behaviour, and anthropomorphism in LLMs induced with drunk language. The simplicity and efficiency of our drunk language inducement approaches position them as potential counters for LLM safety tuning, highlighting significant risks to LLM safety.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Jailbreaking, one of 12 directions in LLM safety and security. Builds on 39 of its 64 references that are in the map. First posted on arXiv 19 Jan 2026.

Builds on

39 of 64 references.

Closest ancestors · 13

Same direction, newest first

  1. 2025Adversarial Poetry as a Universal Single-Turn Jailbreak Mechanism in Large Language Models19 Nov
  2. 2025Anyone Can Jailbreak: Prompt-Based Attacks on LLMs and T2Is29 Jul
  3. 2025Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy26 Mar
  4. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks2 Apr
  5. 2024Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia8 Feb
  6. 2024How Johnny Can Persuade LLMs to Jailbreak Them: Rethinking Persuasion to Challenge AI Safety by Humanizing LLMs12 Jan
  7. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automatically4 Dec
  8. 2023Jailbreaking Black Box Large Language Models in Twenty Queries12 Oct
  9. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attacks5 Oct
  10. 2023GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts19 Sep
  11. 2023Detecting Language Model Attacks with Perplexity27 Aug
  12. 2023Universal and Transferable Adversarial Attacks on Aligned Language Models27 Jul
1 more
  1. 2023Jailbroken: How Does LLM Safety Training Fail?5 Jul

Other references · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2017Proximal Policy Optimization Algorithmscited by 14,441
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  5. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  6. 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,235
  7. 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,106
  8. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 847
  9. 2017DailyDialog: A Manually Labelled Multi-turn Dialogue Datasetcited by 649
  10. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  11. 2020Artificial Intelligence, Values and Alignmentcited by 443
  12. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
14 more
  1. 2023Multi-step Jailbreaking Privacy Attacks on ChatGPTcited by 320
  2. 2023Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theorycited by 218
  3. 2022Why Should Adversarial Perturbations be Imperceptible? Rethink the Research Paradigm in Adversarial NLPcited by 99
  4. 2023Backdoor Attacks for In-Context Learning with Language Modelscited by 92
  5. 2024Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Surveycited by 86
  6. 2024Uncovering Safety Risks of Large Language Models through Concept Activation Vectorcited by 63
  7. 2024What Makes and Breaks Safety Fine-tuning? A Mechanistic Studycited by 54
  8. 2024Scaling Trends for Data Poisoning in LLMscited by 26
  9. 2024Privacy Preserving Prompt Engineering: A Surveycited by 24
  10. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 22
  11. 2025DrunkAgent: Stealthy Memory Corruption in LLM-Powered Recommender Agentscited by 12
  12. 2025Bullying the Machine: How Personas Increase LLM Vulnerabilitycited by 8
  13. 2016A Computational Approach to Automatic Prediction of Drunk Textingcited by 1
  14. 2018Understanding Psycholinguistic Behavior of predominant drunk texters in Social Mediacited by 1

Built on by

Not cited yet.