mlsanityData to 7 Oct 2026

Think Like a Person Before Responding: A Multi-Faceted Evaluation of Persona-Guided LLMs for Countering Hate

arXiv 2506.04043 ↗First posted 4 Jun 2025cs.CL cs.AI cs.CYcited by 1

On the map: LLM reasoning → Reasoning benchmarks and evaluation

Abstract (arXiv)

Automated counter-narratives (CN) offer a promising strategy for mitigating online hate speech, yet concerns about their affective tone, accessibility, and ethical risks remain. We propose a framework for evaluating Large Language Model (LLM)-generated CNs across four dimensions: persona framing, verbosity and readability, affective tone, and ethical robustness. Using GPT-4o-Mini, Cohere's CommandR-7B, and Meta's LLaMA 3.1-70B, we assess three prompting strategies on the MT-Conan and HatEval datasets. Our findings reveal that LLM-generated CNs are often verbose and adapted for people with college-level literacy, limiting their accessibility. While emotionally guided prompts yield more empathetic and readable responses, there remain concerns surrounding safety and effectiveness.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 9 of its 37 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

9 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs8 Nov

Other references · 8

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2024GPT-4o System Cardcited by 4,467
  3. 2023Mistral 7Bcited by 3,065
  4. 2021Human-in-the-Loop for Data Collection: a Multi-Target Counter Narrative Dataset to Fight Online Hate Speechcited by 81
  5. 2022Human-Machine Collaboration Approaches to Build a Dialogue Dataset for Hate Speech Counteringcited by 40
  6. 2023Understanding Counterspeech for Online Harm Mitigationcited by 17
  7. 2024On Zero-Shot Counterspeech Generation by LLMscited by 17
  8. 2024Decoding Hate: Exploring Language Models' Reactions to Hate Speechcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Contextualized Counterspeech Can Be More Persuasive Than Generic Counterspeechcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026CATCH-ME if you RAG: a dataset of Contextually Annotated multi-Turn Counterspeech against Hate and Misinformation Exchanges
  2. 2026Persona Prompting as a Lens on LLM Social Reasoning
  3. 2025Algorithmic Fairness in NLP: Persona-Infused LLMs for Human-Centric Hate Speech Detection
  4. 2025CSEval: Towards Automated, Multi-Dimensional, and Reference-Free Counterspeech Evaluation using Auto-Calibrated LLMs
  5. 2026A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and Refinement
  6. 2025Confident, Calibrated, or Complicit: Safety Alignment and Ideological Bias in LLM Hate Speech Detection
  7. 2026Attribute-Based Diagnosis of LLM Alignment with Hate Speech Annotations
  8. 2025Evaluating Large Language Models for Detecting Antisemitism