Language Models Show Stable Value Orientations Across Diverse Role-Plays

• URL: http://arxiv.org/abs/2408.09049v1
• Date: Fri, 16 Aug 2024 23:24:10 GMT
• Title: Language Models Show Stable Value Orientations Across Diverse Role-Plays
• Authors: Bruce W. Lee, Yeongheon Lee, Hyunsoo Cho,
• Abstract summary: 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.
• Score: 4.906478894661688
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We demonstrate that large language models (LLMs) exhibit consistent value orientations despite adopting diverse personas, revealing a persistent inertia in their responses that remains stable across the variety of roles they are prompted to assume. To systematically explore this phenomenon, we introduce the role-play-at-scale methodology, which involves prompting LLMs with randomized, diverse personas and analyzing the macroscopic trend of their responses. Unlike previous works that simply feed these questions to LLMs as if testing human subjects, our role-play-at-scale methodology diagnoses inherent tendencies in a systematic and scalable manner by: (1) prompting the model to act in different random personas and (2) asking the same question multiple times for each random persona. This approach reveals consistent patterns in LLM responses across diverse role-play scenarios, indicating deeply encoded inherent tendencies. Our findings contribute to the discourse on value alignment in foundation models and demonstrate the efficacy of role-play-at-scale as a diagnostic tool for uncovering encoded biases in LLMs.

Related papers

• CLASH: Evaluating Language Models on Judging High-Stakes Dilemmas from Multiple Perspectives [3.7731230532888036]
  CLASH (Character perspective-based LLM Assessments in Situations with High-stakes) is a dataset consisting of 345 high-impact dilemmas along with 3,795 individual perspectives of diverse values. Even the strongest models, such as GPT-4o and Claude-Sonnet, achieve less than 50% accuracy in identifying situations where the decision should be ambivalent.
  arXiv  Detail & Related papers  (2025-04-15T02:54:16Z)
• Beyond Self-Reports: Multi-Observer Agents for Personality Assessment in Large Language Models [2.7010154811483167]
  This paper introduces a novel multi-observer framework for Large language models (LLMs) personality assessment. Instead of relying solely on self-assessments, our approach employs multiple observer agents configured with a specific relationship context. Our experiments reveal that LLMs possess systematic biases in self-report personality ratings.
  arXiv  Detail & Related papers  (2025-04-11T10:03:55Z)
• Disentangling Length Bias In Preference Learning Via Response-Conditioned Modeling [87.17041933863041]
  We introduce a Response-conditioned Bradley-Terry (Rc-BT) model that enhances the reward model's capability in length bias mitigating and length instruction following. We also propose the Rc-DPO algorithm to leverage the Rc-BT model for direct policy optimization (DPO) of large language models.
  arXiv  Detail & Related papers  (2025-02-02T14:50:25Z)
• Few-shot Steerable Alignment: Adapting Rewards and LLM Policies with Neural Processes [50.544186914115045]
  Large language models (LLMs) are increasingly embedded in everyday applications. Ensuring their alignment with the diverse preferences of individual users has become a critical challenge. We present a novel framework for few-shot steerable alignment.
  arXiv  Detail & Related papers  (2024-12-18T16:14:59Z)
• 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)
• Unified Generative and Discriminative Training for Multi-modal Large Language Models [88.84491005030316]
  Generative training has enabled Vision-Language Models (VLMs) to tackle various complex tasks. Discriminative training, exemplified by models like CLIP, excels in zero-shot image-text classification and retrieval. This paper proposes a unified approach that integrates the strengths of both paradigms.
  arXiv  Detail & Related papers  (2024-11-01T01:51:31Z)
• Diverging Preferences: When do Annotators Disagree and do Models Know? [92.24651142187989]
  We develop a taxonomy of disagreement sources spanning 10 categories across four high-level classes. We find that the majority of disagreements are in opposition with standard reward modeling approaches. We develop methods for identifying diverging preferences to mitigate their influence on evaluation and training.
  arXiv  Detail & Related papers  (2024-10-18T17:32:22Z)
• Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
  Large language models (LLMs) generate content that can undermine trust in online discourse. Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-AI collaboration. To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
  arXiv  Detail & Related papers  (2024-10-18T08:14:10Z)
• Uncovering Factor Level Preferences to Improve Human-Model Alignment [58.50191593880829]
  We introduce PROFILE, a framework that uncovers and quantifies the influence of specific factors driving preferences. ProFILE's factor level analysis explains the 'why' behind human-model alignment and misalignment. We demonstrate how leveraging factor level insights, including addressing misaligned factors, can improve alignment with human preferences.
  arXiv  Detail & Related papers  (2024-10-09T15:02:34Z)
• Bias and Toxicity in Role-Play Reasoning [6.868242720276291]
  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.
  arXiv  Detail & Related papers  (2024-09-21T02:09:13Z)
• Thinking Before Speaking: A Role-playing Model with Mindset [0.6428333375712125]
  Large Language Models (LLMs) are skilled at simulating human behaviors. These models tend to perform poorly when confronted with knowledge that the assumed role does not possess. We propose a Thinking Before Speaking (TBS) model in this paper.
  arXiv  Detail & Related papers  (2024-09-14T02:41:48Z)
• Covert Bias: The Severity of Social Views' Unalignment in Language Models Towards Implicit and Explicit Opinion [0.40964539027092917]
  We evaluate the severity of bias toward a view by using a biased model in edge cases of excessive bias scenarios. Our findings reveal a discrepancy in LLM performance in identifying implicit and explicit opinions, with a general tendency of bias toward explicit opinions of opposing stances. The direct, incautious responses of the unaligned models suggest a need for further refinement of decisiveness.
  arXiv  Detail & Related papers  (2024-08-15T15:23:00Z)
• Social Debiasing for Fair Multi-modal LLMs [55.8071045346024]
  Multi-modal Large Language Models (MLLMs) have advanced significantly, offering powerful vision-language understanding capabilities. However, these models often inherit severe social biases from their training datasets, leading to unfair predictions based on attributes like race and gender. This paper addresses the issue of social biases in MLLMs by i) Introducing a comprehensive Counterfactual dataset with Multiple Social Concepts (CMSC) and ii) Proposing an Anti-Stereotype Debiasing strategy (ASD)
  arXiv  Detail & Related papers  (2024-08-13T02:08:32Z)
• PersLLM: A Personified Training Approach for Large Language Models [66.16513246245401]
  We propose PersLLM, integrating psychology-grounded principles of personality: social practice, consistency, and dynamic development. We incorporate personality traits directly into the model parameters, enhancing the model's resistance to induction, promoting consistency, and supporting the dynamic evolution of personality.
  arXiv  Detail & Related papers  (2024-07-17T08:13:22Z)
• Interpreting Bias in Large Language Models: A Feature-Based Approach [0.0]
  Large Language Models (LLMs) have showcased remarkable performance across various natural language processing (NLP) tasks. This paper investigates the propagation of biases within LLMs through a novel feature-based analytical approach.
  arXiv  Detail & Related papers  (2024-06-18T07:28:15Z)
• Deep Bayesian Active Learning for Preference Modeling in Large Language Models [84.817400962262]
  We propose the Bayesian Active Learner for Preference Modeling (BAL-PM) for Preference Modeling. BAL-PM requires 33% to 68% fewer preference labels in two popular human preference datasets and exceeds previous Bayesian acquisition policies. Our experiments demonstrate that BAL-PM requires 33% to 68% fewer preference labels in two popular human preference datasets and exceeds previous Bayesian acquisition policies.
  arXiv  Detail & Related papers  (2024-06-14T13:32:43Z)
• Chain-of-Thought Prompting for Demographic Inference with Large Multimodal Models [58.58594658683919]
  Large multimodal models (LMMs) have shown transformative potential across various research tasks. Our findings indicate LMMs possess advantages in zero-shot learning, interpretability, and handling uncurated 'in-the-wild' inputs. We propose a Chain-of-Thought augmented prompting approach, which effectively mitigates the off-target prediction issue.
  arXiv  Detail & Related papers  (2024-05-24T16:26:56Z)
• Explaining Large Language Models Decisions Using Shapley Values [1.223779595809275]
  Large language models (LLMs) have opened up exciting possibilities for simulating human behavior and cognitive processes. However, the validity of utilizing LLMs as stand-ins for human subjects remains uncertain. This paper presents a novel approach based on Shapley values to interpret LLM behavior and quantify the relative contribution of each prompt component to the model's output.
  arXiv  Detail & Related papers  (2024-03-29T22:49:43Z)
• Characterizing Truthfulness in Large Language Model Generations with Local Intrinsic Dimension [63.330262740414646]
  We study how to characterize and predict the truthfulness of texts generated from large language models (LLMs) We suggest investigating internal activations and quantifying LLM's truthfulness using the local intrinsic dimension (LID) of model activations.
  arXiv  Detail & Related papers  (2024-02-28T04:56:21Z)
• Exploring Value Biases: How LLMs Deviate Towards the Ideal [57.99044181599786]
  Large-Language-Models (LLMs) are deployed in a wide range of applications, and their response has an increasing social impact. We show that value bias is strong in LLMs across different categories, similar to the results found in human studies.
  arXiv  Detail & Related papers  (2024-02-16T18:28:43Z)
• Modulation of viability signals for self-regulatory control [1.370633147306388]
  We revisit the role of instrumental value as a driver of adaptive behavior. For reinforcement learning tasks, the distribution of preferences replaces the notion of reward.
  arXiv  Detail & Related papers  (2020-07-18T01:11:51Z)

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.