AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

The Other Mind: How Language Models Exhibit Human Temporal Cognition

Lingyu Li, Yang Yao, Yixu Wang, Chunbo Li, Yan Teng, Yingchun Wang

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Reasoning mechanisms and failure modes · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
scale up model size in the year similarity judgment taskQwen2.5 and Llama 3 instruct models · year-pair similarity judgment (1525-2524)fit to reference-log-linear distanceImproved
model years as years instead of plain numbers in the prompt (ablation)similarity judgment task · year vs number controlbest-fitting distance (R2)Mixed
use reference-log-linear distance (reference 2025) instead of plain log-linear distance to predict year judgments (ablation)LLM year similarity · year-pair similarity judgmentR2Improved
scale up model size for neuron activation patterntemporal-preferential neurons · mean activation vs yearlogarithmic-like compressionImproved
increase model depth within layers for log encoding of past yearsQwen2.5-72B-Instruct neurons · layer-wise regression on log distance to 2025R2: R2 of 0.756 at layer 71Improved
compare past vs future years in neural codingLLM temporal neurons · year similarity judgmentsimilarity of year pairsMixed
go from shallow to deep layers for probing year distanceslinear probes on residual stream · similarity judgment hidden statesadjusted R2Mixed
in Qwen models, let reference-distance representation emerge in late layersQwen2.5 series · linear probesadjusted R2 of log-linear distanceHurt
fit reference point as free parameter instead of fixing at 2025 (ablation)reference-log-linear distance · year similarityinterpretability of fitHurt
analyze embedding models of year stringsQwen3-Embedding-8B, text-embedding-3-large, Gemini-embedding-001 · MDS of year embeddingsstructure of year spaceNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy