The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models

• URL: http://arxiv.org/abs/2605.06196v1
• Date: Thu, 07 May 2026 13:08:19 GMT
• Title: The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models
• Abstract summary: We show that large language models encode social roles, from micro-level individual experience to macro-level organizational, institutional, or national reasoning.<n>Our findings suggest that social role granularity is not merely a stylistic surface feature, but a structured, ordered, and causally manipulable latent direction in language model behavior.
• Score: 61.32031248060941
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) are routinely prompted to take on social roles ranging from individuals to institutions, yet it remains unclear whether their internal representations encode the granularity of such roles, from micro-level individual experience to macro-level organizational, institutional, or national reasoning. We show that they do. We define a contrast-based Granularity Axis as the difference between mean macro- and micro-role hidden states. In Qwen3-8B, this axis aligns with the principal axis (PC1) of the role representation space at cosine 0.972 and accounts for 52.6% of its variance, indicating that granularity is the dominant geometric axis organizing prompted social roles. We construct 75 social roles across five granularity levels and collect 91,200 role-conditioned responses over shared questions and prompt variants, then extract role-level hidden states and project them onto the axis. Role projections increase monotonically across all five levels, remain stable across layers, prompt variants, endpoint definitions, held-out splits, and score-filtered subsets, and transfer to Llama-3.1-8B-Instruct. The axis is also causally relevant: activation steering along it shifts response granularity in the predicted direction, with Llama moving from 2.00 to 3.17 on a five-point macro scale under positive steering on prompts that admit local responses. The two models differ in controllability, suggesting that steering depends on each model's default operating regime. Overall, our findings suggest that social role granularity is not merely a stylistic surface feature, but a structured, ordered, and causally manipulable latent direction in role-conditioned language model behavior.

Related papers

• Role Steering of Language Models for Social Simulations [1.593682229070013]
  Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated population.<n>We introduce an activation-steering screening workflow for role-conditioned agents.<n>We apply the workflow to a mixed 275-role inventory with 228 role-agnostic questions, GPT-4.1-mini prompted role references, and GPT-4.1-mini judges.
  arXiv  Detail & Related papers  (2026-07-09T22:07:27Z)
• RoleCDE:Benchmarking and Mitigating Role-Alignment Trade-offs in Role-Playing Agents [22.61759060826869]
  We introduce RoleCDE, the first benchmark designed to evaluate RPAs under structured conflicts between role-specific values and alignment-oriented constraints.<n>The benchmark is constructed at scale, covering approximately 8k diverse role profiles and scenarios and nearly 24k dilemma instances across three difficulty levels and eight role categories.
  arXiv  Detail & Related papers  (2026-06-01T01:56:27Z)
• When Roles Fail: Epistemic Constraints on Advocate Role Fidelity in LLM-Based Political Statement Analysis [0.0]
  This paper provides the first systematic empirical test of the assumption that models will reliably maintain their assigned roles.<n>We measure role fidelity across 60 political statements using four metrics: Role Drift Index (RDI), Drift Distance (EDD), Directional Drift Index (DDI), and Entropy-based Role Stability (ERS)<n>We identify two failure modes - the Epistemic Floor Effect (fact-check results create an absolute lower bound below which the legitimizing role cannot be maintained) and Role-Prior Conflict (training-time knowledge overrides role instructions for factually unambiguous statements)
  arXiv  Detail & Related papers  (2026-04-29T21:50:28Z)
• How Controllable Are Large Language Models? A Unified Evaluation across Behavioral Granularities [75.10343190811592]
  Large Language Models (LLMs) are increasingly deployed in socially sensitive domains.<n>Our benchmark offers a principled and interpretable framework for safe and controllable behavior.
  arXiv  Detail & Related papers  (2026-03-03T03:50:13Z)
• How role-play shapes relevance judgment in zero-shot LLM rankers [15.11127856890218]
  Large Language Models (LLMs) have emerged as promising zero-shot rankers.<n>Their performance is highly sensitive to prompt formulation.<n>In particular, role-play prompts, where the model is assigned a functional role or identity, often give more robust and accurate relevance rankings.
  arXiv  Detail & Related papers  (2025-10-20T13:39:48Z)
• Evaluating LLM Alignment on Personality Inference from Real-World Interview Data [7.061237517845673]
  Large Language Models (LLMs) are increasingly deployed in roles requiring nuanced psychological understanding.<n>Their ability to interpret human personality traits, a critical aspect of such applications, remains unexplored.<n>We introduce a novel benchmark comprising semi-structured interview transcripts paired with validated continuous Big Five trait scores.
  arXiv  Detail & Related papers  (2025-09-16T16:54:35Z)
• SpeechRole: A Large-Scale Dataset and Benchmark for Evaluating Speech Role-Playing Agents [72.79816494079833]
  Role-playing agents have emerged as a promising paradigm for achieving personalized interaction and emotional resonance.<n>Existing research primarily focuses on the textual modality, neglecting the critical dimension of speech in realistic interactive scenarios.<n>We construct SpeechRole-Data, a large-scale, high-quality dataset that comprises 98 diverse roles and 112k speech-based single-turn and multi-turn conversations.
  arXiv  Detail & Related papers  (2025-08-04T03:18:36Z)
• RoleMRC: A Fine-Grained Composite Benchmark for Role-Playing and Instruction-Following [31.80357046048002]
  Role-playing is important for Large Language Models to follow diverse instructions.<n>Existing role-playing datasets mostly contribute to controlling role style and knowledge boundaries.<n>We introduce a fine-grained role-playing and instruction-following benchmark, named RoleMRC.
  arXiv  Detail & Related papers  (2025-02-17T03:08:37Z)
• When Prompting Fails to Sway: Inertia in Moral and Value Judgments of Large Language Models [4.906478894661688]
  Large Language Models (LLMs) exhibit non-deterministic behavior, and prompting has emerged as a primary method for steering their outputs toward desired directions.<n>One popular strategy involves assigning a specific "persona" to the model to induce more varied and context-sensitive responses, akin to the diversity found in human perspectives.<n>Our experiments demonstrate that LLMs maintain consistent value orientations.<n>In particular, we observe a persistent inertia in their responses, where certain moral and value dimensions, especially harm avoidance and fairness, remain distinctly skewed in one direction despite varied persona settings.
  arXiv  Detail & Related papers  (2024-08-16T23:24:10Z)
• SocialBench: Sociality Evaluation of Role-Playing Conversational Agents [85.6641890712617]
  Large language models (LLMs) have advanced the development of various AI conversational agents. SocialBench is the first benchmark designed to evaluate the sociality of role-playing conversational agents at both individual and group levels. We find that agents excelling in individual level does not imply their proficiency in group level.
  arXiv  Detail & Related papers  (2024-03-20T15:38:36Z)
• 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)
• 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)
• RODE: Learning Roles to Decompose Multi-Agent Tasks [69.56458960841165]
  Role-based learning holds the promise of achieving scalable multi-agent learning by decomposing complex tasks using roles. We propose to first decompose joint action spaces into restricted role action spaces by clustering actions according to their effects on the environment and other agents. By virtue of these advances, our method outperforms the current state-of-the-art MARL algorithms on 10 of the 14 scenarios that comprise the challenging StarCraft II micromanagement benchmark.
  arXiv  Detail & Related papers  (2020-10-04T09:20:59Z)

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.