Model editing aims to correct errors in large, pretrained models by replacing model generations with user-provided responses. Existing editors assume a single target answer for each edit. However, many real tasks inherently entail uncertainty, resulting in multiple plausible answers with varying likelihoods in user feedback. Such feedback forms a target distribution to not only correct but also calibrate model generations. We therefore propose SoftEdit, the first model editor to leverage uncertainty in user responses and perform one-shot calibration during editing. To generalize calibration to unseen samples, SoftEdit uses co-plausibility relationships between answers while preserving real distributional shifts, balancing the new distributional generality-locality tradeoff. Across three language models, three vision-language models, and two large datasets, SoftEdit achieves state-of-the-art performance, ultimately showing that uncertainty in user responses enables generalizable calibration of pretrained models beyond single-answer corrections.
Figures & tables
Figure 1: Soft model editing edits inherently uncertain tasks and performs targeted calibration beyond single-answer correction, introducing a new distributional generality–locality tradeoff.
Figure 2: Visualization of changes in the local distribution field of a real edit from VQAv2 as SoftEdit objectives are progressively applied to edit LLaVA-1.5-7B . The xy -plane is a PCA projection of neighbors’ last-token hidden states; the z -axis shows the distributional alignment towards the edit’s target distribution. SoftEdit ( Lalign+Lgen+Lloc ) calibrates the edit ( alignment→1 at the large red point), generalizes calibration to distributionally equivalent neighbors ( alignment→1 at other red points) without overwriting distributional shifts in locality samples (low alignment to edit target at black points).
Figure 3: Semantically similar queries can have largely different target distributions, in VLMs (on VQAv2) and LLMs (on ProtoQA). Each point is a pair of semantically related queries, with cosine similarity of their last-layer hidden states (x-axis) and answer distribution alignment ( 1−JS , y-axis).
Table 1: Batch editing results on VLMs and LLMs using the VQAv2 and ProtoQA datasets.
Alignment does not eliminate behavioral errors in language models. Models may still refuse benign requests, call unnecessary tools, or yield to false user claims. Current methods mitigate such errors as a computation problem, and rarely explore if the desired behavior is already encoded in the model's representation. Motivated by the observation that behavior-relevant information remains linearly decodable from the final hidden state even when the resulting logits produce the undesired behavior, we introduce HeadEdit, a gradient-free method that calibrates model behavior through the unembedding matrix. HeadEdit extracts a low-rank behavioral subspace from paired completions and uses each prompt's coordinates within it to generate a vocabulary-wide correction, thereby implementing implicitly adaptive steering without manually specified target tokens or parameter updates. HeadEdit improves all nine experimental settings across three tasks and three model families, with negligible inference overhead and no systematic loss of general capabilities. It also reveals a connection to gradient-based alignment. HeadEdit's low-dimensional representation partly predicts how preference tuning changes output logits on unseen prompts. The subspace learned from the model can also be reused after tuning, improving performance without re-extracting or retuning. These results show that HeadEdit provides a practical, lightweight, and interpretable way to calibrate model behavior through the unembedding matrix.
Zirui He, Haiyan Zhao, Jingyu Hu +5
New Jersey Institute of Technology · University of Bristol · Kuaishou Technology +1
A central desideratum in model editing is generalization to complex tasks, which prior work formalizes under a direct generalization paradigm: treating and evaluating LLM behavior as an input-output mapping and expecting a factual update to alter outputs on reasoning tasks. Yet despite substantial empirical effort, the field consensus remains that such generalization is highly challenging and elusive. However, when we deploy the latest models in an in-the-wild chatbot-user setting, we surprisingly find that even classical editing methods exhibit remarkably fluent generalization behavior. This motivates us to revisit the obstacles to generalization and the limitations of the prevailing paradigm. We find that direct generalization is fundamentally constrained both theoretically and practically: theoretically, it suffers from an identifiability issue; and practically, existing approaches attempting to circumvent this are further hindered by the ambiguity of their constructed biases and by vulnerability to being overridden by other factors such as optimization dynamics. We instead identify compositional generalization, empowered by the increasingly strong reasoning and composition abilities of modern LLMs, as a theoretically grounded and empirically validated alternative. We validate this phenomenon across multiple models and editing methods, showing that such generalization behavior is widespread. Overall, we argue that generalizable model editing could be more than direct generalization, and call for a paradigm shift toward more generalizable and practically deployable knowledge update techniques.
Xiaotian Ye, Chunyao Yang, Xiaohan Wang +4
University of Cambridge · NLPR, MAIS, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of the Chinese Academy of Sciences +3
A central challenge in large language model (LLM) editing is capability preservation: methods that successfully change targeted behavior can quietly game the editing proxy and corrupt general capabilities, producing degenerate behaviors reminiscent of proxy/reward hacking. We present CrispEdit, a scalable and principled second-order editing algorithm that treats capability preservation as an explicit constraint, unifying and generalizing several existing editing approaches. CrispEdit formulates editing as constrained optimization and enforces the constraint by projecting edit updates onto the low-curvature subspace of the capability-loss landscape. At the crux of CrispEdit is expressing capability constraint via Bregman divergence, whose quadratic form yields the Gauss-Newton Hessian exactly and even when the base model is not trained to convergence. We make this second-order procedure efficient at the LLM scale using Kronecker-factored approximate curvature (K-FAC) and a novel matrix-free projector that exploits Kronecker structure to avoid constructing massive projection matrices. Across standard model-editing benchmarks, CrispEdit achieves high edit success while keeping capability degradation below 1% on average across datasets, significantly improving over prior editors.