Bias and Toxicity in Role-Play Reasoning

• URL: http://arxiv.org/abs/2409.13979v1
• Date: Sat, 21 Sep 2024 02:09:13 GMT
• Title: Bias and Toxicity in Role-Play Reasoning
• Authors: Jinman Zhao, Zifan Qian, Linbo Cao, Yining Wang, Yitian Ding,
• Abstract summary: Role-play in the Large Language Model (LLM) is a crucial technique that enables models to adopt specific perspectives. We demonstrate that role-play also carries potential risks.
• Score: 6.868242720276291
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Role-play in the Large Language Model (LLM) is a crucial technique that enables models to adopt specific perspectives, enhancing their ability to generate contextually relevant and accurate responses. By simulating different roles, theis approach improves reasoning capabilities across various NLP benchmarks, making the model's output more aligned with diverse scenarios. However, in this work, we demonstrate that role-play also carries potential risks. We systematically evaluate the impact of role-play by asking the language model to adopt different roles and testing it on multiple benchmarks that contain stereotypical and harmful questions. Despite the significant fluctuations in the benchmark results in different experiments, we find that applying role-play often increases the overall likelihood of generating stereotypical and harmful outputs.

Related papers

• Systematic Bias in Large Language Models: Discrepant Response Patterns in Binary vs. Continuous Judgment Tasks [13.704342633541454]
  Large Language Models (LLMs) are increasingly used in tasks such as psychological text analysis and decision-making in automated systems. This study examines how different response format: binary versus continuous, may systematically influence LLMs' judgments.
  arXiv  Detail & Related papers  (2025-04-28T03:20:55Z)
• Benchmarking Adversarial Robustness to Bias Elicitation in Large Language Models: Scalable Automated Assessment with LLM-as-a-Judge [0.0]
  Large Language Models (LLMs) have revolutionized artificial intelligence, driving advancements in machine translation, summarization, and conversational agents. Recent studies indicate that LLMs remain vulnerable to adversarial attacks designed to elicit biased responses. This work proposes a scalable benchmarking framework to evaluate LLM robustness against adversarial bias elicitation.
  arXiv  Detail & Related papers  (2025-04-10T16:00:59Z)
• Reversal Blessing: Thinking Backward May Outpace Thinking Forward in Multi-choice Questions [51.61404787000037]
  Language models usually use left-to-right (L2R) autoregressive factorization. We investigate whether alternative factorizations of the text distribution could be beneficial in some tasks.
  arXiv  Detail & Related papers  (2025-02-25T18:30:25Z)
• Benchmarking Bias in Large Language Models during Role-Playing [21.28427555283642]
  We introduce BiasLens, a fairness testing framework designed to expose biases in Large Language Models (LLMs) during role-playing. Our approach uses LLMs to generate 550 social roles across a comprehensive set of 11 demographic attributes, producing 33,000 role-specific questions. Using the generated questions as the benchmark, we conduct extensive evaluations of six advanced LLMs released by OpenAI, Mistral AI, Meta, Alibaba, and DeepSeek. Our benchmark reveals 72,716 biased responses across the studied LLMs, with individual models yielding between 7,754 and 16,963 biased responses.
  arXiv  Detail & Related papers  (2024-11-01T13:47:00Z)
• Controlling Risk of Retrieval-augmented Generation: A Counterfactual Prompting Framework [77.45983464131977]
  We focus on how likely it is that a RAG model's prediction is incorrect, resulting in uncontrollable risks in real-world applications. Our research identifies two critical latent factors affecting RAG's confidence in its predictions. We develop a counterfactual prompting framework that induces the models to alter these factors and analyzes the effect on their answers.
  arXiv  Detail & Related papers  (2024-09-24T14:52:14Z)
• Language Models Show Stable Value Orientations Across Diverse Role-Plays [4.906478894661688]
  We show that large language models (LLMs) exhibit consistent value orientations despite adopting diverse personas. We introduce the role-play-at-scale methodology, which involves prompting LLMs with randomized, diverse personas. This approach reveals consistent patterns in LLM responses across diverse role-play scenarios, indicating deeply encoded inherent tendencies.
  arXiv  Detail & Related papers  (2024-08-16T23:24:10Z)
• Evaluating Interventional Reasoning Capabilities of Large Language Models [58.52919374786108]
  Large language models (LLMs) can estimate causal effects under interventions on different parts of a system. We conduct empirical analyses to evaluate whether LLMs can accurately update their knowledge of a data-generating process in response to an intervention. We create benchmarks that span diverse causal graphs (e.g., confounding, mediation) and variable types, and enable a study of intervention-based reasoning.
  arXiv  Detail & Related papers  (2024-04-08T14:15:56Z)
• On the Decision-Making Abilities in Role-Playing using Large Language Models [6.550638804145713]
  Large language models (LLMs) are increasingly utilized for role-playing tasks. This paper focuses on evaluating the decision-making abilities of LLMs post role-playing.
  arXiv  Detail & Related papers  (2024-02-29T02:22:23Z)
• Enhancing Role-playing Systems through Aggressive Queries: Evaluation and Improvement [17.5855800570993]
  Large Language Models (LLMs) have propelled dialogue generation into new realms, particularly in the field of role-playing systems (RPSs) Existing LLM-based RPSs still struggle to align with roles when handling intricate and trapped queries in boundary scenarios. We design the Modular ORchestrated Trap-setting Interaction SystEm (MORTISE) to benchmark and improve the role-playing LLMs' performance.
  arXiv  Detail & Related papers  (2024-02-16T12:12:05Z)
• Causal Feature Selection for Responsible Machine Learning [14.082894268627124]
  The need for responsible machine learning has emerged, focusing on aligning ML models to ethical and social values. This survey addresses four main issues: interpretability, fairness, adversarial generalization, and domain robustness.
  arXiv  Detail & Related papers  (2024-02-05T03:20:28Z)
• Large Language Models are Superpositions of All Characters: Attaining Arbitrary Role-play via Self-Alignment [62.898963074989766]
  We introduce Ditto, a self-alignment method for role-play. This method creates a role-play training set comprising 4,000 characters, surpassing the scale of currently available datasets by tenfold. We present the first comprehensive cross-supervision alignment experiment in the role-play domain.
  arXiv  Detail & Related papers  (2024-01-23T03:56:22Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection [74.51523859064802]
  We introduce a new framework called Self-Reflective Retrieval-Augmented Generation (Self-RAG) Self-RAG enhances an LM's quality and factuality through retrieval and self-reflection. It significantly outperforms state-of-the-art LLMs and retrieval-augmented models on a diverse set of tasks.
  arXiv  Detail & Related papers  (2023-10-17T18:18:32Z)
• RoleLLM: Benchmarking, Eliciting, and Enhancing Role-Playing Abilities of Large Language Models [107.00832724504752]
  We introduce RoleLLM, a framework to benchmark, elicit, and enhance role-playing abilities in Large Language Models (LLMs) By Context-Instruct and RoleGPT, we create RoleBench, the first systematic and fine-grained character-level benchmark dataset for role-playing with 168,093 samples.
  arXiv  Detail & Related papers  (2023-10-01T17:52:59Z)
• Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts [9.399159332152013]
  This study investigates the behaviors of Large Language Models (LLMs) when faced with conflicting prompts versus their internal memory. This will help to understand LLMs' decision mechanism and also benefit real-world applications, such as retrieval-augmented generation (RAG)
  arXiv  Detail & Related papers  (2023-09-29T17:26:03Z)
• Harnessing Perceptual Adversarial Patches for Crowd Counting [92.79051296850405]
  Crowd counting is vulnerable to adversarial examples in the physical world. This paper proposes the Perceptual Adrial Patch (PAP) generation framework to learn the shared perceptual features between models.
  arXiv  Detail & Related papers  (2021-09-16T13:51:39Z)
• Multilingual Multi-Aspect Explainability Analyses on Machine Reading Comprehension Models [76.48370548802464]
  This paper focuses on conducting a series of analytical experiments to examine the relations between the multi-head self-attention and the final MRC system performance. We discover that passage-to-question and passage understanding attentions are the most important ones in the question answering process. Through comprehensive visualizations and case studies, we also observe several general findings on the attention maps, which can be helpful to understand how these models solve the questions.
  arXiv  Detail & Related papers  (2021-08-26T04:23:57Z)
• ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models [64.03398193325572]
  Inference attacks against Machine Learning (ML) models allow adversaries to learn about training data, model parameters, etc. We concentrate on four attacks - namely, membership inference, model inversion, attribute inference, and model stealing. Our analysis relies on a modular re-usable software, ML-Doctor, which enables ML model owners to assess the risks of deploying their models.
  arXiv  Detail & Related papers  (2021-02-04T11:35:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.