LLM activations encode current and prior entities in orthogonal slots, but models only use the current slot for explicit factual retrieval despite prior-slot information being linearly decodable.
arXiv preprint arXiv:2510.06182 , year=
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
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.
citation-role summary
method 1
citation-polarity summary
years
2026 7roles
method 1polarities
use method 1representative citing papers
Standard circuit discovery methods produce dataset-specific circuits rather than task-general ones, and a new clustering-based method discovers multiple more faithful circuits per dataset.
A four-step recipe partitions the input space using interchange intervention behavior to diagnose where causal abstractions hold and to guide improvements, demonstrated by recovering a full hypothesis from scratch in a toy logic task.
Large language models encode relational bindings via a cell-based representation: a low-dimensional linear subspace in which each cell corresponds to an entity-relation index pair and attributes are retrieved from the matching cell.
Causal interventions reveal a retrieval-conditioned rebinding circuit in attention heads that supports dynamic entity tracking in Gemma and Llama models, with family-specific representational signatures.
LLM agent pairs in a resource allocation negotiation game fail to reach Pareto-optimal outcomes due to dynamic grounding failures such as loss of interaction history, anchoring, and referential errors.
citing papers explorer
-
Slot Machines: How LLMs Keep Track of Multiple Entities
LLM activations encode current and prior entities in orthogonal slots, but models only use the current slot for explicit factual retrieval despite prior-slot information being linearly decodable.
-
Data-driven Circuit Discovery for Interpretability of Language Models
Standard circuit discovery methods produce dataset-specific circuits rather than task-general ones, and a new clustering-based method discovers multiple more faithful circuits per dataset.
-
Bucketing the Good Apples: A Method for Diagnosing and Improving Causal Abstraction
A four-step recipe partitions the input space using interchange intervention behavior to diagnose where causal abstractions hold and to guide improvements, demonstrated by recovering a full hypothesis from scratch in a toy logic task.
-
Cell-Based Representation of Relational Binding in Language Models
Large language models encode relational bindings via a cell-based representation: a low-dimensional linear subspace in which each cell corresponds to an entity-relation index pair and attributes are retrieved from the matching cell.
-
A retrieval conditioned rebinding circuit for dynamic entity tracking in large language models
Causal interventions reveal a retrieval-conditioned rebinding circuit in attention heads that supports dynamic entity tracking in Gemma and Llama models, with family-specific representational signatures.
-
Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation
LLM agent pairs in a resource allocation negotiation game fail to reach Pareto-optimal outcomes due to dynamic grounding failures such as loss of interaction history, anchoring, and referential errors.
- Persistent Priors, Preserved Targets: A Stroop-Style Paradigm for Lexical Override