STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs

• URL: http://arxiv.org/abs/2608.08164v1
• Date: Sat, 08 Aug 2026 14:46:22 GMT
• Title: STEMMA: An Adversarial Multi-Agent Framework for Evaluating Self-Identity Consistency in LLMs
• Abstract summary: We argue that apart from the functional knowledge, student models also learn behavioral patterns, specifically how a model represents its own identity.<n>We introduce STEMMA, a multi-modal and multi-agent framework in which role specific agents collaboratively probe self identification behavior.<n>Our results show that to an extent most models are vulnerable to inconsistencies in self-representations.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge Distillation is a widely adopted technique in the training and fine-tuning of large language models (LLMs) enabling transfer of structured information and functional behavior from a large teacher model to a smaller student model while significantly reducing computational costs. However, as the use of distillation increases in both scale and complexity it raises an important question about what kind of knowledge is really transferred from the teacher model. In this work, we argue that apart from the functional knowledge, student models also learn behavioral patterns, specifically how a model represents its own identity raising concerns about output homogeneity, model biases, and accountability. To address this challenge, we introduce STEMMA, a multi-modal and multi-agent framework in which role specific agents collaboratively probe self identification behavior in different models. We also contribute a set of adversarial prompts designed manually to evaluate identity consistency in LLMs. Our results show that to an extent most models are vulnerable to inconsistencies in self-representations.

Related papers

• Learning Task-Agnostic Representations through Multi-Teacher Distillation [59.488314181423284]
  We introduce a task-agnostic framework based on a majority vote" objective function.<n>We demonstrate that this function is bounded by the mutual information between student and teachers' embeddings.<n>Our method effectively leverages teacher diversity, resulting in representations enabling better performance for a wide range of downstream tasks.
  arXiv  Detail & Related papers  (2025-10-21T14:36:33Z)
• UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models [62.76435672183968]
  We introduce a novel framework, namely UNIFORM, for knowledge transfer from a diverse set of off-the-shelf models into one student model.<n>We propose a dedicated voting mechanism to capture the consensus of knowledge both at the logit level and at the feature level.<n>Experiments demonstrate that UNIFORM effectively enhances unsupervised object recognition performance compared to strong knowledge transfer baselines.
  arXiv  Detail & Related papers  (2025-08-27T00:56:11Z)
• Perspectives for Direct Interpretability in Multi-Agent Deep Reinforcement Learning [0.41783829807634765]
  Multi-Agent Deep Reinforcement Learning (MADRL) was proven efficient in solving complex problems in robotics or games.<n>This paper advocates for direct interpretability, generating post hoc explanations directly from trained models.<n>We explore modern methods, including relevance backpropagation, knowledge edition, model steering, activation patching, sparse autoencoders and circuit discovery.
  arXiv  Detail & Related papers  (2025-02-02T09:15:27Z)
• Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control [44.326363467045496]
  Large Language Models (LLMs) have become a critical area of research in Reinforcement Learning from Human Feedback (RLHF) representation engineering offers a new, training-free approach. This technique leverages semantic features to control the representation of LLM's intermediate hidden states. It is difficult to encode various semantic contents, like honesty and safety, into a singular semantic feature.
  arXiv  Detail & Related papers  (2024-11-04T08:36:03Z)
• Interactive DualChecker for Mitigating Hallucinations in Distilling Large Language Models [7.632217365130212]
  Large Language Models (LLMs) have demonstrated exceptional capabilities across various machine learning (ML) tasks. These models can produce hallucinations, particularly in domains with incomplete knowledge. We introduce DualChecker, an innovative framework designed to mitigate hallucinations and improve the performance of both teacher and student models.
  arXiv  Detail & Related papers  (2024-08-22T12:04:04Z)
• A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
  In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. We present a generative latent variable model for self-supervised learning. We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
  arXiv  Detail & Related papers  (2024-02-02T13:31:17Z)
• MoMA: Momentum Contrastive Learning with Multi-head Attention-based Knowledge Distillation for Histopathology Image Analysis [4.5677296928097055]
  A lack of quality data is a common issue when it comes to a specific task in computational pathology.<n>We propose to exploit knowledge distillation, i.e., utilize the existing model to learn a new, target model.<n>We employ a student-teacher framework to learn a target model from a pre-trained, teacher model without direct access to source data.
  arXiv  Detail & Related papers  (2023-08-31T08:54:59Z)
• Prototype-guided Cross-task Knowledge Distillation for Large-scale Models [103.04711721343278]
  Cross-task knowledge distillation helps to train a small student model to obtain a competitive performance. We propose a Prototype-guided Cross-task Knowledge Distillation (ProC-KD) approach to transfer the intrinsic local-level object knowledge of a large-scale teacher network to various task scenarios.
  arXiv  Detail & Related papers  (2022-12-26T15:00:42Z)
• Multi-Agent Imitation Learning with Copulas [102.27052968901894]
  Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions. In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems. Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
  arXiv  Detail & Related papers  (2021-07-10T03:49:41Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

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.