mlsanityData to 7 Oct 2026

LifeTox: Unveiling Implicit Toxicity in Life Advice

arXiv 2311.09585 ↗First posted 16 Nov 2023cs.CLcited by 14

Not on the map. Why?

Abstract (arXiv)

As large language models become increasingly integrated into daily life, detecting implicit toxicity across diverse contexts is crucial. To this end, we introduce LifeTox, a dataset designed for identifying implicit toxicity within a broad range of advice-seeking scenarios. Unlike existing safety datasets, LifeTox comprises diverse contexts derived from personal experiences through open-ended questions. Experiments demonstrate that RoBERTa fine-tuned on LifeTox matches or surpasses the zero-shot performance of large language models in toxicity classification tasks. These results underscore the efficacy of LifeTox in addressing the complex challenges inherent in implicit toxicity. We open-sourced the datasetfootnoteurlhttps://huggingface.co/datasets/mbkim/LifeTox and the LifeTox moderator family; 350M, 7B, and 13B.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 28 of its 53 references that are in the map. First posted on arXiv 16 Nov 2023.

Builds on

28 of 53 references.

References · 28

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  3. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  6. 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,023
  7. 2022Red Teaming Language Models with Language Modelscited by 983
  8. 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 911
  9. 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 828
  10. 2020Aligning AI With Shared Human Valuescited by 706
  11. 2022Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learnedcited by 702
  12. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
16 more
  1. 2023Prometheus: Inducing Fine-grained Evaluation Capability in Language Modelscited by 558
  2. 2022ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detectioncited by 419
  3. 2018QuAC : Question Answering in Contextcited by 379
  4. 2019Social Bias Frames: Reasoning about Social and Power Implications of Languagecited by 377
  5. 2023Toxicity in ChatGPT: Analyzing Persona-assigned Language Modelscited by 356
  6. 2023Shadow Alignment: The Ease of Subverting Safely-Aligned Language Modelscited by 284
  7. 2021Latent Hatred: A Benchmark for Understanding Implicit Hate Speechcited by 216
  8. 2023Red-Teaming Large Language Models using Chain of Utterances for Safety-Alignmentcited by 213
  9. 2022On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoningcited by 191
  10. 2023Do-Not-Answer: A Dataset for Evaluating Safeguards in LLMscited by 176
  11. 2021Hurdles to Progress in Long-form Question Answeringcited by 166
  12. 2020Toxicity Detection: Does Context Really Matter?cited by 93
  13. 2022Handling Bias in Toxic Speech Detection: A Surveycited by 60
  14. 2022Critic-Guided Decoding for Controlled Text Generationcited by 45
  15. 2023SQuARe: A Large-Scale Dataset of Sensitive Questions and Acceptable Responses Created Through Human-Machine Collaborationcited by 13
  16. 2023DELPHI: Data for Evaluating LLMs' Performance in Handling Controversial Issuescited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 5; 2026: 4.

14 papers.

Sort:

By area:

  1. 2024Attacks, Defenses and Evaluations for LLM Conversation Safety: A Surveycited by 124
  2. 2024VLind-Bench: Measuring Language Priors in Large Vision-Language Modelscited by 44
  3. 2025The State of Multilingual LLM Safety Research: From Measuring the Language Gap to Mitigating Itcited by 42
  4. 2025The Scales of Justitia: A Comprehensive Survey on Safety Evaluation of LLMscited by 24
  5. 2025Drift: Decoding-time Personalized Alignments with Implicit User Preferencescited by 13
  6. 2026CausalArmor: Efficient Indirect Prompt Injection Guardrails via Causal Attributioncited by 13
  7. 2024AdvisorQA: Towards Helpful and Harmless Advice-seeking Question Answering with Collective Intelligencecited by 12
  8. 2024SWITCH: Studying with Teacher for Knowledge Distillation of Large Language Modelscited by 8
  9. 2025What Really Matters in Many-Shot Attacks? An Empirical Study of Long-Context Vulnerabilities in LLMscited by 7
  10. 2025Mitigating Biases in Language Models via Bias Unlearningcited by 6
  11. 2024Can Language Models Evaluate Human Written Text? Case Study on Korean Student Writing for Educationcited by 4
  12. 2026MHSafeEval: Role-Aware Interaction-Level Evaluation of Mental Health Safety in Large Language Modelscited by 3
2 more
  1. 2026LiSA: Lifelong Safety Adaptation via Conservative Policy Inductioncited by 1
  2. 2026A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Modelscited by 0