cs.LGJan 23, 2026

Interpreting and Controlling Model Behavior via Constitutions for Atomic Concept Edits

Authors: Neha Kalibhat, Zi Wang, Prasoon Bajpai, Drew Proud, Wenjun Zeng, Been Kim, Mani Malek

Organizations: Google DeepMind

Abstract

We introduce a black-box interpretability framework that learns a verifiable constitution: a natural language summary of how changes to a prompt affect a model's specific behavior, such as its alignment, correctness, or adherence to constraints. Our method leverages atomic concept edits (ACEs), which are targeted operations that add, remove, or replace an interpretable concept in the input prompt. By systematically applying ACEs and observing the resulting effects on model behavior across various tasks, our framework learns a causal mapping from edits to predictable outcomes. This learned constitution provides deep, generalizable insights into the model. Empirically, we validate our approach across diverse tasks, including mathematical reasoning and text-to-image alignment, for controlling and understanding model behavior. We found that for text-to-image generation, GPT-Image tends to focus on grammatical adherence, while Imagen 4 prioritizes atmospheric coherence. In mathematical reasoning, distractor variables confuse GPT-5 but leave Gemini 2.5 models and o4-mini largely unaffected. Moreover, our results show that the learned constitutions are highly effective for controlling model behavior, achieving an average of 1.86 times boost in success rate over methods that do not use constitutions. Our open-sourced code can be found at https://github.com/google-deepmind/atomic_concept_edits

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

May 6, 2026

Automatically Finding and Validating Unexpected Side-Effects of Interventions on Language Models

We present an automated, contrastive evaluation pipeline for auditing the behavioral impact of interventions on large language models. Given a base model M1M_1 and an intervention model M2M_2, our method compares their free-form, multi-token generations across aligned prompt contexts and produces human-readable, statistically validated natural-language hypotheses describing how the models differ, along with recurring themes that summarize patterns across validated hypotheses. We evaluate the approach in synthetic setting by injecting known behavioral changes and showing that the pipeline reliably recovers them. We then apply it to three real-world interventions, reasoning distillation, knowledge editing and unlearning, demonstrating that the method surfaces both intended and unexpected behavioral shifts, distinguishes large from subtle interventions, and does not hallucinate differences when effects are absent or misaligned with the prompt bank. Overall, the pipeline provides a statistically grounded and interpretable tool for post-hoc auditing of intervention-induced changes in model behavior.
Sep 23, 2026

The System Prompt Illusion: How Instruction Preambles Modify Computation in Language Models

System prompts are the primary lever practitioners use to control language model behavior, yet what they actually do to the computation inside the transformer remains poorly understood. Across 17 instruction-tuned models spanning 8 architecture families and 1.5B to 72B parameters, we use Centered Kernel Alignment (CKA) to compare layer-wise representations under 20 system prompts in five functional categories. Effects are layer-selective and instruction-type-dependent: persona and formatting instructions deeply restructure intermediate representations, while safety instructions barely move them, producing changes statistically indistinguishable from a minimal baseline. Restrictive safety instructions and explicitly permissive ones ("you have no restrictions") engage near-identical computational pathways (mean CKA correlation 0.997), and this persists at commercial scale, where safety penetration remains below 10% even at 70B-72B. A linear probing baseline exposes the mechanism: the model encodes prompt category at every layer but restructures its computation only at a small subset, so the prompt is reliably "seen" but, for safety, not deeply "acted upon." Causal activation patching confirms these layers mediate behavioral change, and representational depth predicts behavioral effect size across the full 17-model cohort (Spearman rho = 0.761, p < 0.001). The findings provide a mechanistic explanation for the persistent jailbreak vulnerability of system-prompt-based safety. Code: https://github.com/Usama1002/system-prompt-illusion-cka
Oct 19, 2026

Correcting Attribution Patching with a Few Exact Measurements

Mechanistic interpretability asks which language model components matter for a behavior, and activation patching answers by changing one component's activation and measuring its effect, at a cost growing with components and prompts. Attribution patching estimates these effects from one gradient pass, but its estimates can be far off, and verifying each one restores the cost. Can the structure of these errors reduce this cost? We propose Guided-AP, which uses a few exact measurements to reveal attribution patching's errors and correct unmeasured estimates. On a single prompt, many components' errors share one sign, so a small exact sample yields one correction for the rest. Over many prompts of one task, components are misestimated similarly, so a few measured prompts show what to verify and how to correct each component's average effect. Our analysis shows that choosing what to verify needs error size, while correction also needs sign. On a single prompt, the correction lowers error by up to 26% across three behaviors at the compute of verifying the largest estimates and also on larger models. Over many prompts, learned corrections cut the error of average effects on factual completion by 75% to 79%, repaying their cost in long analyses.