Factual recall in language models is typically framed as retrieving a factual association: a subject--relation pair maps to a single object. However, many facts are context-dependent: the same pair maps to different objects depending on a condition such as time. We introduce anchored factual recall, in which the model receives an explicit conditioning expression, an anchor, and must select the object valid under it. This raises questions that single-object recall does not: where the anchor enters the computation, what it changes, and how that change selects the answer. Focusing on temporal anchors, we answer them with causal interventions on four open-weight models on English prompts and identify two routes. In a subject-mediated route, the anchor resolves the final subject-token representation to the queried year, and the relation redistributes the readout of this state across attention heads. In a direct route] the final position attends to the anchor, and upper-layer MLPs turn this signal into a preference for the time-appropriate object. The two routes are parallel channels: their contributions add up, most queries use both, and their balance depends on the query, e.g., on the relation, consistently across models. This reframes mechanistic accounts of factual recall from retrieving a single stored object to selecting among context-dependent alternatives.
Figures & tables
Figure 1: Two routes integrate the temporal anchor into factual recall. Subject-mediated : the anchor resolves the subject representation to 2020, and the relation sets how the final position reads it. Direct : the final position reads the anchor itself, and MLPs turn it into a preference for Juventus . The two routes are used jointly on most queries, with a balance that varies across queries.
Figure 2: Q1: the anchor enters the computation at two points. Attention knockout of S←A degrades the prediction in early-to-middle layers, knockout of L←A from the middle layers onward, whereas knockout of R←A has little effect.
Figure 3: The subject state selectively supports the year-appropriate object. Patching the reference subject state into the contrast run raises the logit of the reference-year object c , lowers the logit of the contrast-year object cˉ , and leaves the mean logit of the other temporal candidates largely unchanged.
Figure 4: The relation redistributes last-subject readout across attention heads. Per-layer total-variation distance between head-normalized last-subject attention distributions (Eq. 2 ): swapping the relation changes the distribution far more than swapping the anchor year.
Figure 5: Relation-sensitive heads causally support the correct prediction. Top-1 flip rate after ablating the last-subject contribution of relation-sensitive, time-sensitive, or contribution-matched random heads (selected on discovery folds; § 4.3.1 ). Error bars: 95% bootstrap CIs.
Figure 6: The direct route acts through final-position MLPs. Value-injection recovery decomposed into MLP-mediated ( RMLP ) and non-MLP ( Rnon-MLP ) components: pinning the MLPs removes nearly all of the recovery.
Figure 7: Upper-layer MLPs are answer-selective. Direct logit attribution: the reference-minus-contrast difference ΔDLA(ℓ) in each final-position MLP’s contribution to the logit margin turns positive over a band of upper layers.
Figure 8: The two routes are parallel channels whose contributions add up, and most instances use both. (a) Gain in the logit margin over the none condition: both routes (left) vs. the two single-route gains, stacked (right). (b) Instances whose margin is raised by at least one route alone, by which routes raise it.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 9: The effect of the anchored subject state is not a shared year offset. Recovery of the logit difference between c and cˉ when the final subject-token state of the contrast run is set to the reference-year state, or to the contrast-year state plus the mean reference-minus-contrast difference of other subjects with the same pair of years. No query position can attend to the anchor in either condition. Shaded bands are 95% bootstrap intervals over subject–relation groups.
Figure 10: Route usage varies across instances. Subject-mediated recovery ( Si ) vs. direct-route recovery ( Di ) per reference–contrast comparison.
Large Language Models (LLMs) suffer from temporal misalignment, often due to the contradictory nature of their training corpora. While current mitigation strategies rely on computationally expensive fine-tuning or context-heavy retrieval augmented generation (RAG), the internal mechanisms governing time-sensitive recall remain under-explored. Unlike prior studies that identify temporal components such as attention heads and MLP layers, we provide the first feature-level map of temporal recall by isolating individual MLP features via transcoder circuit tracing. We identify three node categories (common temporal, common to the year, and chrono-semantic) which interact to generate a temporal filter during factual recall. By analysing Gemma 2 2B, LLaMA 3.2 1B, and Qwen3-4B, we show that these features do not follow a simple linear pipeline but represent time through a parallel and mixed syntactic-semantic interplay across layers. We additionally discover a class of higher-layer temporal components invisible to existing EAP-IG methods, establishing transcoders as a more complete lens for temporal interpretability in time-sensitive factual recall. These findings present MLP components for potential targeted interventions in time-sensitive factual recall
We reproduce and stress-test the work of Yu et al. (2023), who characterize how language models (LMs) arbitrate between memorized knowledge and contradictory in-context statements. We replicate their world-capitals experiments on 31 models spanning Pythia, GPT-2, Qwen3, and Ministral families, including base and post-trained variants, and extend evaluations to five additional knowledge relation types from the ParaConflict dataset. We empirically confirm most of their original findings: larger models and higher-frequency entities tend to favor memorized answers, with substantial family-level variance. However, several conclusions do not generalize cleanly: entity-frequency effects disappear on Qwen3-14B and 32B; post-training shifts the memory-context trade-off inconsistently across families; question phrasing alone can change a model's reliance on memorized knowledge by up to 80 percentage points; and semantically unrelated prose can mimic coherent supporting context. Our results clarify where Yu et al.'s claims hold and to what extent they generalize to other prompts.
Guilhem Fouilhé, Nicholas Asher, Philippe Muller
IRIT ANITI · IRIT CNRS · IRIT Université de Toulouse
While large language models have achieved remarkable performance in complex tasks, they still need a memory system to utilize historical experience in long-term interactions. Existing memory methods (e.g., A-Mem, Mem0) place excessive emphasis on organizing interactions by frequently rewriting them, however, this heavy reliance on summarization risks diluting essential contextual nuances and obscuring key retrieval features. To bridge this gap, we introduce AnchorMem, a novel memory framework inspired by the Proust Phenomenon in cognitive science, where a specific anchor triggers a holistic recollection. We propose a method that decouples the retrieval unit from the generation context. AnchorMem extracts atomic facts from interaction history to serve as retrieval anchors, while preserving the original context as the immutable context. To reveal implicit narrative cues, we construct an associative event graph that uses higher-order event links that bind sets of related facts into shared event representations, strengthening cross-memory integration without relying on generic entities as bridges. During retrieval, the system anchors queries to specific facts and events to locate relevant memories, but reconstructs the context using the associated raw chunks and events. Our method reconciles fine-grained retrieval with the contextual integrity of interactions. Experiments across three closed-source and open-source models on the LoCoMo benchmark demonstrate that AnchorMem significantly outperforms baselines. Code is available at https://github.com/RayNeo-AI-2025/AnchorMem.
Zhanyu Shen, Sijie Cheng, Zhicheng Guo +3
College of Computer Science and Software Engineering, Shenzhen University · Tsinghua University