Chi Andrew Zhang

Chi Zhang, Mengqi Zhang, Xiaotian Ye et al.

Sequential knowledge editing in large language models often causes catastrophic collapse of the model's general abilities, especially for parameter-modifying methods. Existing approaches mitigate this issue through heuristic constraints on parameter updates, yet the mechanisms underlying such degradation remain insufficiently understood. In this work, we present a spectral analysis of sequential knowledge editing and show that a model's general abilities are closely associated with dominant singular directions of pretrained weight matrices. These directions are highly sensitive to perturbations and are progressively disrupted by repeated edits, closely tracking the collapse in both editing efficacy and general performance. Building on this insight, we propose REVIVE, a plug-and-play framework that stabilizes sequential editing by explicitly preserving the dominant singular subspace. REVIVE represents parameter updates in the spectral basis of the original weights and filters components that would interfere with the protected region. Extensive experiments across multiple models and benchmarks show that REVIVE consistently improves editing efficacy while substantially preserving general abilities under long-horizon sequential editing, including extreme settings with up to 20,000 edits.

Rohan Bhatnagar, Youran Sun, Chi Andrew Zhang et al.

Hallucination in large language models (LLMs) can be understood as a failure of faithful readout: although internal representations may encode uncertainty about a query, decoding pressures still yield a fluent answer. We propose lightweight residual probes that read hallucination risk directly from intermediate hidden states of question tokens, motivated by the hypothesis that these layers retain epistemic signals that are attenuated in the final decoding stage. The probe is a small auxiliary network whose computation is orders of magnitude cheaper than token generation and can be evaluated fully in parallel with inference, enabling near-instantaneous hallucination risk estimation with effectively zero added latency in low-risk cases. We deploy the probe as an agentic critic for fast selective generation and routing, allowing LLMs to immediately answer confident queries while delegating uncertain ones to stronger verification pipelines. Across four QA benchmarks and multiple LLM families, the method achieves strong AUROC and AURAC, generalizes under dataset shift, and reveals interpretable structure in intermediate representations, positioning fast internal uncertainty readout as a principled foundation for reliable agentic AI.