(1) VLM Editing on VQAv2 (1000 unfiltered samples)
(2) LLM editing on protoqa (1000 unfiltered samples)
D.2 Backbone VLMs and LLMs
Edited VLMs. LLaVA-1.5-7B ( Liu et al., 2024 ) connects a CLIP ViT-L/14 vision encoder to a Vicuna-7B language model through a two-layer MLP projector and is trained using a two-stage visual instruction-tuning pipeline. InstructBLIP-7B ( Dai et al., 2023 ) is an instruction-tuned BLIP-2 variant that employs a frozen image encoder and an instruction-aware Q-Former to extract visual features conditioned on the input instruction, which are projected into a frozen Vicuna-7B language model for generation. Qwen3-VL-4B-Instruct ( Yang et al., 2025 ) employs a Vision Transformer for variable-resolution image encoding and integrates multi-level visual features into a 4B-parameter transformer decoder through DeepStack, with Interleaved-MRoPE for unified spatial–temporal positional modeling.
Edited LLMs. Llama-3.1-8B-Instruct ( Grattafiori et al., 2024 ) is an 8B-parameter decoder-only transformer with grouped query attention and rotary position embeddings, supporting a 128K-token context window and post-trained for instruction following. Mistral-7B-Instruct ( Jiang et al., 2023 ) is a 7B-parameter decoder-only transformer that employs sliding window attention and grouped query attention for efficient long-context inference, with an instruction-tuned variant for instruction following. Qwen2.5-7B-Instruct ( Qwen et al., 2025 ) is a 7B-parameter decoder-only transformer with grouped query attention, rotary position embeddings, and SwiGLU activations, post-trained for instruction following and general-purpose language understanding and generation.
D.3 Baseline Model Editing Methods
We compare SoftEdit against state-of-the-art model editing methods adapted for one-shot calibration of pretrained large language models. Three baseline editing methods—Fine-tuning, MEND, and GRACE—have been adapted to edit both LLMs and VLMs. We additionally include the state-of-the-art VLM editors BalancEdit and ReasonEdit, and the text-only editors IKE and AlphaEdit for LLMs. All baselines are adapted to a soft-label variant that uses the multi-answer distribution instead of a single target answer to supervise the editing, ensuring each method has access to the same distributional target as SoftEdit. Specifically, (1) Fine-tuning (FT) has been adopted to update the weight of a selected layer of the pretrained model on each edit via gradient descent. It is the simplest weight-editing baseline but is prone to catastrophic collapse as edits accumulate. (2) MEND ( Mitchell et al., 2021 ) trains a lightweight meta-network that decomposes and transforms the raw fine-tuning gradient into a low-rank parameter update, enabling fast edits without per-edit iterative optimization. (3) GRACE ( Hartvigsen et al., 2023 ) maintains a discrete key–value codebook alongside the frozen model, where each edit stores a hidden activation as a key and learns a corresponding replacement activation as its value; at inference time, the value is retrieved only when an input falls within the associated local influence radius. (4) In-context Knowledge Editing (IKE) ( Zheng et al., 2023 ; Guo et al., 2025 ) is a retrieval-based, training-free editor that represents edits as textual demonstrations and retrieves relevant edits at inference time to prepend to the input context, guiding the model toward the updated knowledge without modifying its parameters. (5) BalancEdit ( Guo et al., 2025 ) extends localized codebook editing to multimodal models by generating positive and negative samples for each edit to estimate its influence scope, which is encoded into a discrete latent-space codebook without modifying the underlying model weights. (6) ReasonEdit ( Qiu et al., 2026 ) stores human-provided reasoning in a codebook and uses a topology-balanced multimodal embedding method to retrieve relevant reasoning at inference time to guide generation. (7) AlphaEdit ( Fang et al., 2025 ) is a locate-then-edit method that constrains parameter updates by projecting them onto the null space of preserved-knowledge activations, reducing interference with previously stored knowledge during sequential editing.
We preserve the original editing mechanisms of prior editors as closely as possible. In addition, we devoted extra tuning effort to GRACE’s retrieval radius using 100 edits for each backbone model to improve its generality on the new dataset. We also used a batch size of 10 instead of 1 for AlphaEdit in sequential editing to improve its performance and ensure competitive and fair comparisons.
D.4 Comparison to Post-training Model Calibration Methods
We compare SoftEdit with five post-training calibration methods: three global calibration methods and two retrieval-based variants we adapt for one-shot localized calibration.
Global calibrators. (1) Temperature Scaling (TS) ( Guo et al., 2017 ) learns a single global temperature from calibration data to rescale model logits, adjusting prediction confidence without changing the predicted ranking. We adapt it to our distributional target by optimizing the temperature to minimize the KL divergence between the temperature-scaled first-token distribution and the human answer distribution across all edits. (2) Batch Calibration (BC) ( Zhou et al., 2024 ) estimates prediction biases from average output scores over a batch of inputs and removes these biases to calibrate predictions. We adopt its labeled variant (BCL), extending the bias correction to the full token vocabulary and selecting the correction strength γ \gamma γ via grid search to minimize KL divergence against human answer distributions. (3) Adaptive Temperature Scaling (ATS) ( Xie et al., 2024 ) trains a lightweight calibration module to predict token-specific temperatures from hidden states, enabling input-dependent calibration of generated token probabilities. We adapt its training objective by replacing the correctness-dependent loss with KL divergence against the target distribution. Adapted one-shot local calibrators. Since these methods are originally designed for global calibration and assume a coherent miscalibration pattern, they may struggle with heterogeneous miscalibration across individual samples. For a more direct comparison, we adapt TS (ATS reduces to the same form in the one-shot setting) and BC into one-shot retrieval-based variants, preserving their core calibration ideas while enabling localized calibration for individual edits. (4) TS-Retrieval fits an independent temperature T e T_{e} T e for each edit by minimizing KL divergence against its target distribution. The temperature is stored alongside the edit’s final-layer last-token hidden state as the retrieval key. At inference, the nearest stored key (by L2 distance) provides the temperature for logit scaling. (5) BC-Retrieval adopts a simple distribution lookup approach, directly storing each edit’s human first-token distribution q e q_{e} q e alongside its final-layer last-token hidden state as the retrieval key. At inference, the nearest stored key (by L2 distance) provides q e q_{e} q e to replace the model’s predicted first-token distribution for a nearby sample. Editor LLaVA-1.5-7B (4,436 errors) InstructBLIP-7B (4,625 errors) Qwen3-4B (4,157 errors) Align SGen-I SGen-T SLoc Acc Gen-I Gen-T Loc Align SGen-I SGen-T SLoc Acc Gen-I Gen-T Loc Align SGen-I SGen-T SLoc Acc Gen-I Gen-T Loc Unedited 0.08 0.16 0.08 0.27 0.02 0.38 0.12 1.00 0.17 0.23 0.17 0.31 0.02 0.35 0.12 1.00 0.11 0.22 0.12 0.51 0.01 0.39 0.11 1.00 TS 0.03 0.05 0.03 0.06 0.02 0.38 0.12 0.98 0.17 0.22 0.16 0.27 0.00 0.35 0.12 1.00 0.13 0.21 0.13 0.31 0.01 0.39 0.11 1.00 BCL 0.00 0.00 0.00 0.00 0.03 0.38 0.13 0.98 0.17 0.23 0.17 0.29 0.02 0.36 0.12 1.00 0.09 0.17 0.10 0.26 0.01 0.39 0.11 1.00 ATS 0.03 0.02 0.03 0.03 0.02 0.38 0.12 0.98 0.18 0.23 0.17 0.28 0.02 0.36 0.12 1.00 0.14 0.21 0.14 0.29 0.01 0.39 0.11 1.00 TS-Retrieval 0.03 0.05 0.03 0.06 0.02 0.38 0.12 1.00 0.18 0.23 0.18 0.29 0.00 0.36 0.12 1.00 0.14 0.21 0.14 0.32 0.02 0.39 0.11 1.00 BC-Retrieval 0.90 0.79 0.86 0.48 0.92 0.83 0.89 0.18 0.88 0.79 0.86 0.50 0.91 0.84 0.89 0.16 0.89 0.73 0.86 0.44 0.90 0.78 0.87 0.15 SoftEdit 0.97 0.78 0.92 0.61 0.99 0.92 0.98 0.92 0.98 0.82 0.88 0.64 1.00 0.98 0.99 0.78 0.89 0.67 0.82 0.65 0.94 0.88 0.93 0.95 (1) VLM Calibration on VQAv2 (19,186 samples) Editor Llama-3.1-8B (8,326 errors) Mistral-7B (7,782 errors) Qwen2.5-7B (7,207 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Unedited 0.04 0.04 0.07 0.01 0.03 1.00 0.03 0.03 0.11 0.02 0.07 1.00 0.04 0.06 0.17 0.00 0.10 1.00 TS 0.02 0.02 0.02 0.00 0.04 1.00 0.01 0.01 0.03 0.00 0.08 1.00 0.02 0.02 0.07 0.01 0.09 1.00 BCL 0.04 0.03 0.06 0.00 0.04 1.00 0.00 0.00 0.00 0.01 0.08 1.00 0.02 0.02 0.05 0.01 0.09 0.99 ATS 0.02 0.02 0.06 0.00 0.04 1.00 0.02 0.00 0.00 0.00 0.08 1.00 0.02 0.02 0.06 0.00 0.09 1.00 TS-Retrieval 0.02 0.02 0.02 0.00 0.03 1.00 0.02 0.01 0.04 0.01 0.07 1.00 0.03 0.03 0.08 0.00 0.10 1.00 BC-Retrieval 0.56 0.52 0.22 0.35 0.32 0.12 0.57 0.53 0.20 0.58 0.53 0.13 0.52 0.47 0.20 0.58 0.54 0.15 SoftEdit 0.95 0.72 0.47 0.98 0.94 0.76 0.93 0.70 0.52 0.98 0.95 0.69 0.93 0.73 0.52 0.98 0.94 0.77 (2) LLM Calibration on ProtoQA (9,762 samples) Table 8: Comparison to post-training calibration baselines on VLMs and LLMs using the VQAv2 and ProtoQA datasets. TS, BCL, and ATS fit a global calibrator on the full edit set; TS-Retrieval and BC-Retrieval retrieve a per-edit temperature scalar or first-token distribution.
Results. As shown in Table 8 , SoftEdit is significantly more effective than post-training calibration methods for heterogeneous, localized calibration of individual edits. First, all three global calibrators fail to improve model generation or calibration over the unedited baseline, even when trained on the provided edit set where the model made errors. We identify two main reasons. (1) These methods assume a coherent global miscalibration pattern, while our edits require heterogeneous, localized corrections. Learning a global temperature, a probability bias vector, or a temperature prediction module can suffer from averaging across diverse calibration needs. (2) These methods adjust token probabilities but do not ensure correct answer ranking and generation. In particular, temperature scaling preserves the original ranking of answers. When the model already ranks an incorrect answer above the human-provided answers, changing the temperature alone cannot correct the ranking. For the adapted one-shot retrieval-based calibrators, TS-Retrieval still fails due to the second reason above: learning an individual temperature for each edit cannot calibrate original-incorrectly ranked answers. BC-Retrieval (directly retrieve the correct first-token probability) improves performance but remains limited for two reasons. (1) Overwriting the same distribution across a semantic neighborhood ignores genuine distribution shifts among nearby samples, resulting in inferior soft locality (SLoc). (2) Replacing only the first-token distribution encourages the model to start with the correct tokens but cannot ensure that it continues to generate the complete answer correctly.
D.5 Additional Ablations
Ablation of retrieval rejection threshold. The retrieval rejection threshold controls the conventional generality–locality tradeoff in retrieval-based model editing by preventing edits from generalizing to semantically unrelated queries, similar to distance-based regularization in prior work ( Hartvigsen et al., 2023 ; Guo et al., 2025 ; Qiu et al., 2026 ) . We compare our automatically selected threshold with fixed distance percentiles of 1, 10, and 50. As shown in Table 9 , higher percentiles allow retrieval over larger distances, improving generality and soft generality but reducing locality. In contrast, lower percentiles restrict retrieval, preserving locality but limiting generality and soft generality. The auto-tuned threshold improves generality, soft generality and soft locality while preserving relatively high conventional locality.
Variant LLaVA-1.5-7B (4,436 errors) InstructBLIP-7B (4,625 errors) Qwen3-4B (4,157 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc pct 1 0.97 0.73 0.52 0.99 0.74 1.00 0.97 0.79 0.60 1.00 0.87 0.85 0.89 0.68 0.62 0.94 0.67 1.00 pct 10 0.97 0.77 0.56 0.99 0.90 0.90 0.97 0.79 0.62 1.00 0.95 0.81 0.89 0.73 0.64 0.94 0.88 0.95 pct 50 0.97 0.85 0.61 0.99 0.95 0.67 0.97 0.81 0.60 1.00 0.97 0.60 0.89 0.74 0.65 0.94 0.90 0.79 auto (SoftEdit) 0.97 0.85 0.61 0.99 0.95 0.90 0.98 0.85 0.64 1.00 0.99 0.78 0.89 0.75 0.65 0.94 0.90 0.95 (1) VLM Editing on VQAv2 (19,186 samples) Variant Llama-3.1-8B (8,326 errors) Mistral-7B (7,782 errors) Qwen2.5-7B (7,207 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc pct 1 0.95 0.14 0.07 0.98 0.17 0.81 0.93 0.06 0.08 0.98 0.10 0.80 0.93 0.04 0.24 0.98 0.08 0.80 pct 10 0.94 0.54 0.30 0.98 0.69 0.75 0.93 0.53 0.42 0.98 0.71 0.77 0.93 0.62 0.40 0.98 0.81 0.79 pct 50 0.94 0.70 0.44 0.98 0.91 0.70 0.93 0.68 0.51 0.98 0.92 0.61 0.93 0.71 0.51 0.98 0.92 0.71 auto (SoftEdit) 0.95 0.72 0.47 0.98 0.94 0.76 0.93 0.70 0.52 0.98 0.95 0.69 0.93 0.73 0.52 0.98 0.94 0.77 (2) LLM Editing on ProtoQA (9,762 samples) Table 9: Retrieval-threshold ablation.
Ablation of LLM paraphrase judge. At inference, before applying a retrieved weight perturbation, we use a lightweight LLM judge ( Qwen2.5-1.5B-Instruct ) to verify whether a new query is a paraphrase of its matched edit’s query, further distinguishing subtle semantic differences between queries with similar embeddings. As shown in Table 10 , for VLMs, the judge provides limited additional benefits, as multimodal embeddings capture subtle visual information along with textual differences to distinguish queries. However, for LLMs, the judge effectively differentiates subtle semantic differences in texts missed by embedding-only retrieval, notably improving locality (Loc) while maintaining comparable performance on other metrics.
Inference cost of retrieval and paraphrase judge. On an A100 GPU, the lightweight Qwen2.5-1.5B-Instruct paraphrase judge adds a modest overhead of 16.1 ± 1.0 ms/query. Including key encoding and lookup, the total inference time increases only from 31.1 to 31.2 ms/query as the number of edits grows from 100 to 4,000. Codebook growth has minimal impact on inference cost: the mean nearest-neighbor retrieval time increases only from 0.04 to 0.20 ms/query.
LLaVA-1.5-7B (4,436 errors) InstructBLIP-7B (4,625 errors) Qwen3-4B (4,157 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc no judge 0.98 0.85 0.61 1.00 0.96 0.93 0.97 0.85 0.64 1.00 0.99 0.75 0.89 0.75 0.65 0.95 0.91 0.95 with judge (SoftEdit) 0.97 0.85 0.61 0.99 0.95 0.92 0.98 0.85 0.64 1.00 0.99 0.78 0.89 0.75 0.65 0.94 0.90 0.95 (1) VLM Editing on VQAv2 (19,186 samples) Llama-3.1-8B (8,326 errors) Mistral-7B (7,782 errors) Qwen2.5-7B (7,207 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc no judge 0.96 0.73 0.47 1.00 0.94 0.54 0.94 0.71 0.52 0.99 0.95 0.35 0.94 0.73 0.50 0.98 0.95 0.54 with judge (SoftEdit) 0.95 0.72 0.47 0.98 0.94 0.76 0.93 0.70 0.52 0.98 0.95 0.69 0.93 0.73 0.52 0.98 0.94 0.77 (2) LLM Editing on ProtoQA (9,762 samples) Table 10: Ablation of the lightweight LLM paraphrase judge (Qwen2.5-1.5B-Instruct).
Ablation of weighted A i j A_{ij} A ij in graph-Laplacian regularization. We ablate the probability-weighted graph-Laplacian regularization by replacing it with unweighted and Frobenius-norm alternatives. As shown in Table 11 , both alternatives achieve generally competitive performance but exhibit decreases in soft generality (SGen) and soft locality (SLoc), with variations across models. Overall, the probability-weighted graph-Laplacian regularization achieves the optimal performances across calibration and conventional editing metrics. We thus adopt weighted formulation to emphasize relationships between more plausible answers, while alternative regularization formulations can also encourage coherent changes in answer probabilities. Variant LLaVA-1.5-7B (4,436 errors) InstructBLIP-7B (4,625 errors) Qwen3-4B (4,157 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc frobenius 0.97 0.84 0.60 0.99 0.95 0.90 0.95 0.83 0.62 0.96 0.98 0.79 0.87 0.75 0.65 0.93 0.92 0.93 unweighted 0.96 0.83 0.60 0.98 0.94 0.91 0.96 0.85 0.63 0.99 0.99 0.78 0.80 0.72 0.60 0.88 0.87 0.93 weighted (SoftEdit) 0.97 0.85 0.61 0.99 0.95 0.92 0.98 0.85 0.64 1.00 0.99 0.78 0.89 0.75 0.65 0.94 0.90 0.95 (1) VLM Editing on VQAv2 (19,186 samples) Variant Llama-3.1-8B (8,326 errors) Mistral-7B (7,782 errors) Qwen2.5-7B (7,207 errors) Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc Align SGen SLoc Acc Gen Loc frobenius 0.93 0.70 0.40 0.97 0.92 0.74 0.90 0.72 0.48 0.96 0.91 0.69 0.91 0.73 0.48 0.95 0.93 0.77 unweighted 0.92 0.69 0.40 0.98 0.92 0.74 0.90 0.70 0.41 0.96 0.91 0.68 0.91 0.73 0.47 0.95 0.93 0.77 weighted (SoftEdit) 0.95 0.72 0.47 0.98 0.94 0.76 0.93 0.70 0.52 0.98 0.95 0.69 0.93 0.73 0.52 0.98 0.94 0.77 (2) LLM Editing on ProtoQA (9,762 samples) Table 11: Ablation of weighted A i j A_{ij} A ij in graph-Laplacian regularization. Sensitivity analysis of λ l o c \lambda_{\mathrm{loc}} λ loc and λ g e n \lambda_{\mathrm{gen}} λ gen auto-tuned using the first k k k edits. As shown in Table 12 , the auto-tuned coefficients are robust to the number of edits used for estimation. Across all six models, the coefficients remain unchanged for k ≥ 50 k\geq 50 k ≥ 50 . We also note that auto-tuning is computationally efficient, requiring only a single forward pass per edit through the original unedited model to compute the initial loss terms, without additional optimization. We use k = 100 k=100 k = 100 in all experiments, while both k = 50 k=50 k = 50 and k = 100 k=100 k = 100 serve as reasonable defaults. k k k LLaVA-1.5-7B InstructBLIP-7B Qwen3-4B Llama-3.1-8B Mistral-7B Qwen2.5-7B λ l o c \lambda_{\mathrm{loc}} λ loc λ g e n \lambda_{\mathrm{gen}} λ gen λ l o c \lambda_{\mathrm{loc}} λ loc λ g e n \lambda_{\mathrm{gen}} λ gen λ l o c \lambda_{\mathrm{loc}} λ loc λ g e n \lambda_{\mathrm{gen}} λ gen λ l o c \lambda_{\mathrm{loc}} λ loc λ g e n \lambda_{\mathrm{gen}} λ gen λ l o c \lambda_{\mathrm{loc}} λ loc λ g e n \lambda_{\mathrm{gen}} λ gen λ l o c \lambda_{\mathrm{loc}} λ loc λ g e n \lambda_{\mathrm{gen}} λ gen 10 0.005 1 0.05 1 0.01 1 0.001 1 0.0001 10 0.0005 5 50 0.005 1 0.05 1 0.05 1 0.001 1 0.0001 10 0.0005 5 100 0.005 1 0.05 1 0.05 1 0.001 1 0.0001 10 0.0005 5 1000 0.005 1 0.05 1 0.05 1 0.001 1 0.0001 10 0.0005 5Table 12: Robust auto-tuned λ l o c \lambda_{\mathrm{loc}} λ loc and λ g e n \lambda_{\mathrm{gen}} λ gen estimated from the first k k k edits. D.6 Additional Results
Table 13: SGen-I on VQAv2, evaluated separately using photometric perturbations and generated image variants. The variant column is the mean [min, max] across t ∈ { 0.0 , 0.3 } t\in\{0.0,0.3\} t ∈ { 0.0 , 0.3 } . Figure 10: Sequential editing performance and computational efficiency across VLM and LLM editors adapted to one-shot calibration. SoftEdit achieves the best alignment, soft generality, and soft locality. Each line corresponds to an edited pretrained model. Figure 11: Ablation of all four loss combinations. L l o c \mathcal{L}_{\mathrm{loc}} L loc is designed to mitigate overgeneralization introduced by L g e n \mathcal{L}_{\mathrm{gen}} L gen ; thus, optimizing L a l i g n + L l o c \mathcal{L}_{\mathrm{align}}+\mathcal{L}_{\mathrm{loc}} L align + L loc is not a primary design choice shown in Fig. 5 . Separate SGen-I evaluations. In Table 4.3 , we report the overall image soft generality (SGen-I) of VLM editors. Here, we separately evaluate SGen-I on photometric perturbations and generated image variants (mean [min, max] over t ∈ { 0.0 , 0.3 } t\in\{0.0,0.3\} t ∈ { 0.0 , 0.3 } variants) in Table 13 . Photometric perturbations preserve the original image semantics, while generated variants assess generalization to unseen but semantically related images. SoftEdit consistently outperforms all baselines on both evaluation sets across three VLMs. Performance is generally lower on generated variants, which may reflect stronger visual variations and uncertainty in their target distributions. Overall, these results show that SoftEdit’s image soft generality improvements extend beyond simple photometric perturbations. Non-aggregated sequential editing. We report the non-aggregated sequential editing performance for each LLM and VLM individually in Fig. 10 .
Additional ablation results on loss functions. We further ablate all four loss combinations, including L align + L loc \mathcal{L}_{\text{align}}+\mathcal{L}_{\text{loc}} L align + L loc , in Fig. 11 . Across all six models, L align + L loc \mathcal{L}_{\text{align}}+\mathcal{L}_{\text{loc}} L align + L loc yields performance similar to L align \mathcal{L}_{\text{align}} L align . Appendix E Limitations SoftEdit has limitations. First, SoftEdit focuses on aleatoric uncertainty : irreducible uncertainty arising from genuine ambiguity or subjective disagreement, where the observed human answer distribution is treated as reliable feedback. In practice, however, human feedback may also contain annotation noise, unreliable answers, or outliers that should not be interpreted as meaningful uncertainty. Distinguishing these cases is an important direction for future work. For example, properties of the observed answer distribution, such as its shape and entropy, could potentially be combined with outlier detection or annotator-consistency signals to identify unreliable answers. Second, SoftEdit inherits a scalability limitation of retrieval-based editors (GRACE, IKE, BalancEdit, ReasonEdit). Although SoftEdit stores only a compact weight perturbation matrix for each edit, the retrieval index and stored perturbations grow with the number of edits. For codebook containing a few thousand edits, as commonly considered in model editing settings, exact nearest-neighbor retrieval is efficient on CPU, with nearly constant latency in practice ( Hartvigsen et al., 2023 ) . As the codebook grows, more efficient GPU usage in retrieval, or advanced search algorithms on CPUs can mitigate retrieval overhead ( Johnson et al., 2019 ; Malkov and Yashunin, 2018 ; Jegou et al., 2010 ) . As the first study of one-shot calibration via model editing, we adopt first-token-based probability estimation following prior work ( Lee et al., 2023 ; Ma et al., 2025 ) . Our primary objective is to investigate local calibration and its distributional generality–locality tradeoff, using the same evaluation procedure for SoftEdit and all adapted editors. In our experiments, shared-first-token answers occur in only 4.65–5.06% of ProtoQA samples and 0.62–0.63% of VQAv2 samples, as determined by tokenization using the three LLMs and three VLMs, respectively. To better distinguish answers sharing the same first token, future work could explore more flexible token-level probabilistic factorizations. Experimentally, for SGen-I, we acknowledge that the target distributions of generated ambiguous images are approximated through latent interpolation, which may introduce evaluation noise. To account for this uncertainty, we report the average performance across multiple interpolation strengths, together with the minimum and maximum scores.