Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context

• URL: http://arxiv.org/abs/2510.06182v1
• Date: Tue, 07 Oct 2025 17:44:30 GMT
• Title: Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
• Abstract summary: A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval.<n>We show that this mechanism generalizes poorly to more complex settings.<n>We develop a causal model combining all three mechanisms that estimates next token distributions with 95% agreement.
• Score: 33.223631694438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A key component of in-context reasoning is the ability of language models (LMs) to bind entities for later retrieval. For example, an LM might represent "Ann loves pie" by binding "Ann" to "pie", allowing it to later retrieve "Ann" when asked "Who loves pie?" Prior research on short lists of bound entities found strong evidence that LMs implement such retrieval via a positional mechanism, where "Ann" is retrieved based on its position in context. In this work, we find that this mechanism generalizes poorly to more complex settings; as the number of bound entities in context increases, the positional mechanism becomes noisy and unreliable in middle positions. To compensate for this, we find that LMs supplement the positional mechanism with a lexical mechanism (retrieving "Ann" using its bound counterpart "pie") and a reflexive mechanism (retrieving "Ann" through a direct pointer). Through extensive experiments on nine models and ten binding tasks, we uncover a consistent pattern in how LMs mix these mechanisms to drive model behavior. We leverage these insights to develop a causal model combining all three mechanisms that estimates next token distributions with 95% agreement. Finally, we show that our model generalizes to substantially longer inputs of open-ended text interleaved with entity groups, further demonstrating the robustness of our findings in more natural settings. Overall, our study establishes a more complete picture of how LMs bind and retrieve entities in-context.

Related papers

• A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models [16.759528230678722]
  We identify a retrieval conditioned rebinding mechanism that encodes swap relevant binding information and reinstates it at readout.<n>Across Gemma and Llama models, this circuit supports rebinding behavior, but the representational signature of the mechanism differs across model families.
  arXiv  Detail & Related papers  (2026-06-07T14:16:44Z)
• Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs [69.28193153685893]
  Large Language Models (LLMs) frequently exhibit strong translation abilities, even without task-specific fine-tuning.<n>To demystify this process, we leverage Sparse Autoencoders (SAEs) and introduce a novel framework for identifying task-specific features.<n>Our work not only decodes a core component of the translation mechanism in LLMs but also provides a blueprint for using internal model mechanism to create more robust and efficient models.
  arXiv  Detail & Related papers  (2026-01-16T06:29:07Z)
• Unifying Tree Search Algorithm and Reward Design for LLM Reasoning: A Survey [92.71325249013535]
  Deliberative tree search is a cornerstone of Large Language Model (LLM) research.<n>This paper introduces a unified framework that deconstructs search algorithms into three core components.
  arXiv  Detail & Related papers  (2025-10-11T03:29:18Z)
• WUGNECTIVES: Novel Entity Inferences of Language Models from Discourse Connectives [28.171845634282576]
  We study whether discourse connectives can inform language models about the world.<n>We present WUGNECTIVES, a dataset of 8,880 stimuli that evaluates LMs' inferences about novel entities.<n>We find that tuning an LM to show reasoning behavior yields noteworthy improvements on most connectives.
  arXiv  Detail & Related papers  (2025-10-10T17:07:45Z)
• Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research [3.1304584228602685]
  I propose five axes of correspondence along which mechanistic claims might generalize.<n>I analyze "1-back attention heads" across pretraining in random seeds of the Pythia models.
  arXiv  Detail & Related papers  (2025-09-26T18:38:16Z)
• Language Models use Lookbacks to Track Beliefs [51.92689607136242]
  We analyze Llama-3-70B-Instruct's ability to reason about characters' beliefs using causal mediation and abstraction.<n>Our work provides insights into the LM's belief tracking mechanisms, taking a step toward reverse-engineering ToM reasoning in LMs.
  arXiv  Detail & Related papers  (2025-05-20T17:59:45Z)
• I Have Covered All the Bases Here: Interpreting Reasoning Features in Large Language Models via Sparse Autoencoders [8.1201445044499]
  Internal mechanisms behind reasoning in LLMs remain unexplored.<n>We employ Sparse Autoencoders to test our hypothesis.<n>Our work provides the first step towards a mechanistic understanding of reasoning in LLMs.
  arXiv  Detail & Related papers  (2025-03-24T16:54:26Z)
• Computation Mechanism Behind LLM Position Generalization [59.013857707250814]
  Large language models (LLMs) exhibit flexibility in handling textual positions.<n>They can understand texts with position perturbations and generalize to longer texts.<n>This work connects the linguistic phenomenon with LLMs' computational mechanisms.
  arXiv  Detail & Related papers  (2025-03-17T15:47:37Z)
• Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals [82.68757839524677]
  Interpretability research aims to bridge the gap between empirical success and our scientific understanding of large language models (LLMs) We propose a formulation of competition of mechanisms, which focuses on the interplay of multiple mechanisms instead of individual mechanisms. Our findings show traces of the mechanisms and their competition across various model components and reveal attention positions that effectively control the strength of certain mechanisms.
  arXiv  Detail & Related papers  (2024-02-18T17:26:51Z)
• How do Language Models Bind Entities in Context? [31.529253469951062]
  Language models (LMs) must bind entities to their attributes to correctly use in-context information. We identify the binding ID mechanism: a general mechanism for solving the binding problem. Our results uncover interpretable strategies in LMs for representing symbolic knowledge in-context.
  arXiv  Detail & Related papers  (2023-10-26T07:10:31Z)
• Dissecting Recall of Factual Associations in Auto-Regressive Language Models [41.71388509750695]
  Transformer-based language models (LMs) are known to capture factual knowledge in their parameters. We study how the model aggregates information about the subject and relation to predict the correct attribute. Our findings introduce a comprehensive view of how factual associations are stored and extracted internally in LMs.
  arXiv  Detail & Related papers  (2023-04-28T11:26:17Z)

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.