CORTEXA
← Browse
arxivcs.CLcs.LG2026-06-25

Forecasting With LLMs: Improved Generalization Through Feature Steering

Humzah Merchant, Bradford Levy

Successful forecasting involves identifying patterns between historical and future states of the world which generalize to future observations. We apply LLMs to a variety of forecasting tasks and inspect their internal states using sparse autoencoders to understand whether they appear to rely on time-specific pieces of knowledge versus generalizable patterns. Our analyses identify features associated with both time-aware reasoning and look-ahead-biased reasoning. We then apply the LLMs to an entirely different domain and intervene on these features. We find that amplifying time-awareness features substantially reduces look-ahead bias on forecasting prompts while preserving general reasoning performance. In contrast, steering the candidate look-ahead-bias features does not produce an effect. These results suggest that interpretable temporal features can be used to causally shift LLMs toward more historically grounded reasoning.

View free PDFSource page

Related papers

arxivcs.LGcs.CL2026-07-02

Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis

Jiatong Li, Weida Wang, Changmeng Zheng, Shufei Zhang, Yatao Bian, Xiao-yong Wei, et al.

Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space. This raises the question of whether molecular LLMs can ge…

View free PDFSource page
arxivcs.LGcs.AIcs.CL2026-06-27Cited by 1

Feature Generation Using LLMs: An Evolutionary Algorithm Approach

Aria Nourbakhsh, Benoît Alcaraz, Christoph Schommer

A crucial step in machine learning pipelines is to present each entity with features or attributes that are representative of the characteristics of the processed entities. Feature engineering is an important step in finding a relation among attributes that otherwise may not be p…

View free PDFSource page
arxivcs.CLcs.AIcs.CEcs.LG2026-06-26

Enhancing Numerical Prediction in LLMs via Smooth MMD Alignment

Zhuo Zuo, Li Yue, Wenhao Zheng, Chenpeng Wang, Xianggen Liu

Despite their strong general capabilities, large language models (LLMs) often remain unreliable when outputs must be numerically precise. A key reason is the training objective: standard cross-entropy treats numeric tokens as unstructured categories and ignores the metric structu…

View free PDFSource page
arxivcs.LGcs.CL2026-07-22

Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects

Seonglae Cho, Zekun Wu, Kleyton Da Costa, Rishi Kalra, Ilham Wicaksono, Adriano Koshiyama

Sparse autoencoder (SAE) features are used to interpret and steer large language models, yet whether a feature's causal role is stable across SAE families remains untested. Single-token features that activate on one vocabulary item provide the diagnostic case where ground truth p…

View free PDFSource page
arxivcs.CLcs.AIcs.LG2026-07-06

EEG-SpikeAgent: Agentic Closed-Loop Program Synthesis for Automated EEG Spike Detection

Sonali Santhosh, Kelly Shuhong Yu, Eugene Chang, Jonathan Kim, Kie Shidara, Danilo Bernardo

Automated detection of interictal epileptiform discharges in scalp electroencephalography (EEG) is clinically important, but recent high-performing deep-learning models often trade interpretability for accuracy. We introduce EEG-SpikeAgent, a closed-loop program-synthesis framewo…

View free PDFSource page