Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models

• URL: http://arxiv.org/abs/2602.07794v1
• Date: Sun, 08 Feb 2026 03:14:39 GMT
• Title: Emergent Structured Representations Support Flexible In-Context Inference in Large Language Models
• Authors: Ningyu Xu, Qi Zhang, Xipeng Qiu, Xuanjing Huang,
• Abstract summary: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning.<n>We investigate the internal processing of LLMs during in-context concept inference.
• Score: 77.98801218316505
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) exhibit emergent behaviors suggestive of human-like reasoning. While recent work has identified structured, human-like conceptual representations within these models, it remains unclear whether they functionally rely on such representations for reasoning. Here we investigate the internal processing of LLMs during in-context concept inference. Our results reveal a conceptual subspace emerging in middle to late layers, whose representational structure persists across contexts. Using causal mediation analyses, we demonstrate that this subspace is not merely an epiphenomenon but is functionally central to model predictions, establishing its causal role in inference. We further identify a layer-wise progression where attention heads in early-to-middle layers integrate contextual cues to construct and refine the subspace, which is subsequently leveraged by later layers to generate predictions. Together, these findings provide evidence that LLMs dynamically construct and use structured, latent representations in context for inference, offering insights into the computational processes underlying flexible adaptation.

Related papers

• The Evolving Nature of Latent Spaces: From GANs to Diffusion [2.9612444540570113]
  We show how diffusion models fragment the burden of representation and thereby challenge assumptions of unified internal space.<n>We argue for a reorientation of how generative AI is understood: not as a direct synthesis of content, but as an emergent configuration of specialized processes.
  arXiv  Detail & Related papers  (2025-10-20T10:20:42Z)
• Implicit Reasoning in Large Language Models: A Comprehensive Survey [67.53966514728383]
  Large Language Models (LLMs) have demonstrated strong generalization across a wide range of tasks.<n>Recent studies have shifted attention from explicit chain-of-thought prompting toward implicit reasoning.<n>This survey introduces a taxonomy centered on execution paradigms, shifting the focus from representational forms to computational strategies.
  arXiv  Detail & Related papers  (2025-09-02T14:16:02Z)
• Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning Dynamics [69.00587226225232]
  We introduce a state-aware transition framework that abstracts CoT trajectories into structured latent dynamics.<n>To characterize the global structure of reasoning, we model their progression as a Markov chain.<n>This abstraction supports a range of analyses, including semantic role identification, temporal pattern visualization, and consistency evaluation.
  arXiv  Detail & Related papers  (2025-08-29T18:53:31Z)
• How do Transformers Learn Implicit Reasoning? [67.02072851088637]
  We study how implicit multi-hop reasoning emerges by training transformers from scratch in a controlled symbolic environment.<n>We find that training with atomic triples is not necessary but accelerates learning, and that second-hop generalization relies on query-level exposure to specific compositional structures.
  arXiv  Detail & Related papers  (2025-05-29T17:02:49Z)
• From Compression to Expression: A Layerwise Analysis of In-Context Learning [24.45948310980883]
  In-context learning (ICL) enables large language models to adapt to new tasks without weight updates by learning from demonstration sequences.<n>We conduct a statistical geometric analysis of ICL representations to investigate how task-specific information is captured across layers.<n>Our findings reveal an intriguing layerwise dynamic in ICL, highlight how structured representations emerge within LLMs, and showcase that analyzing internal representations can facilitate a deeper understanding of model behavior.
  arXiv  Detail & Related papers  (2025-05-22T22:22:03Z)
• Interpreting token compositionality in LLMs: A robustness analysis [10.777646083061395]
  Constituent-Aware Pooling (CAP) is a methodology designed to analyse how large language models process linguistic structures.<n>CAP intervenes in model activations through constituent-based pooling at various model levels.<n>Our findings highlight fundamental limitations in current transformer architectures regarding compositional semantics processing and model interpretability.
  arXiv  Detail & Related papers  (2024-10-16T18:10:50Z)
• Distributional Associations vs In-Context Reasoning: A Study of Feed-forward and Attention Layers [49.80959223722325]
  We study the distinction between feed-forward and attention layers in large language models.<n>We find that feed-forward layers tend to learn simple distributional associations such as bigrams, while attention layers focus on in-context reasoning.
  arXiv  Detail & Related papers  (2024-06-05T08:51:08Z)
• Calibrating Reasoning in Language Models with Internal Consistency [18.24350001344488]
  Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks.<n>LLMs often generate text with obvious mistakes and contradictions.<n>In this work, we investigate reasoning in LLMs through the lens of internal representations.
  arXiv  Detail & Related papers  (2024-05-29T02:44:12Z)
• Guiding the PLMs with Semantic Anchors as Intermediate Supervision: Towards Interpretable Semantic Parsing [57.11806632758607]
  We propose to incorporate the current pretrained language models with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines.
  arXiv  Detail & Related papers  (2022-10-04T07:27:29Z)

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.