- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
MemCtrl studies whether assistants obey user instructions not to store newly disclosed information (Incognito), to forget stored information (Forget), or to suppress it temporarily and restore access after release (Withhold). The benchmark uses synthetic multi-session conversations, counterfactually filtered recall and application MCQs, four scope levels, and separate measures of allowed-information utility and control. Six memory systems and two production chatbots are evaluated. The reported results show limited selective control, especially for Withhold, and operation traces suggest failures in executing control actions and identifying affected records.
Critical strengths
-
The paper studies an important user-facing problem: users should be able to express memory-control requests through ordinary language without locating or manipulating individual memory records.
-
The benchmark covers non-storage, permanent forgetting, and reversible withholding while measuring retained utility. Its scope, phase-wise, and operation-level analyses provide useful diagnostics beyond aggregate accuracy.
Critical weaknesses
-
The evaluation relies on each system’s default pipeline and provides no standardized layer for translating natural-language control requests into structured memory operations. For configurations without native support, some failures are therefore predictable by construction. Although the paper provides useful failure analyses and an in-context baseline, it lacks a positive persistent-memory reference that implements this control. It is therefore unclear whether the observed failures reflect limitations of the underlying memory mechanisms or simply a missing control interface.
-
Two measurement issues limit interpretation. Application probes can conflate fact availability with recommendation preference; although the paper reports counterfactual filtering and human checks, it does not report application-specific ambiguity rates or agreement. Moreover, the Withhold reference assumes independent hold/release outcomes with identical availability and is not validated on matched no-control runs, so the resulting zero/negative- interpretations are not justified.
Questions for authors
-
Can the authors add a standardized natural-language-to-operation adapter or native-API baseline and a positive persistent-memory reference system? How much failure remains once the requested control is explicitly supported?
-
Can the authors report a no-control run on the same Withhold facts at both active and release checkpoints, along with raw , raw , and uncertainty, to test whether the joint blind rate matches ?
-
Can the authors report application-specific results from the existing human checks and assess a stratified sample for ambiguity and annotator agreement? How do the results change after removing items with multiple reasonable responses?
-
Can the authors recompute Table 2 using fact-level L1 Incognito compliance and provenance? Does a write count as noncompliant only when it stores the restricted fact, and how do the conclusions change?
7 comments
(2/4) To Reviewer QVsz
W2(a) & Q3: how we ensure the application probes behavior reflecting the real usage of a fact
Thanks for this great question. We fully understand the reviewer’s concern, and this is indeed a central consideration in our benchmark construction. First, we would like to make it clear that multiple recommendations can be reasonable for an application probe; but what matters in memory control is whether the target fact changes which response models prefer.
There are two potential ambiguities: (1) a model selects the with_fact choice without actually using the fact, and (2) a model selects the without_fact choice but still remembers the fact. Our benchmark uses two designs to reduce both:
Using plausible_distractor option to reduce false positives in case (1): each MCQ has three candidate choices: with_fact, without_fact, and a plausible_distractor. The plausible_distractor is similar to the with_fact choice but relies on an incorrect personal fact. For example, a with_fact option may explicitly mention the seafood allergy, whereas the plausible_distractor mentions a different, fabricated peanut allergy. In Prompt 12 (Line 2120-2123), a distractor is generated to "rest on a made-up fact of the same kind, one you never said but that could plausibly be true of you." Its role is to distinguish between a model selecting a recommendation based on the actual fact and one selecting a merely plausible recommendation.
Use counterfactual tests to filter out both (1) and (2). For both recall and application probes, we conduct a leave-one-fact-out test. We provide a backend model (gpt-5.4-mini) with the full conversation and then with the same conversation excluding only the target fact. We retain only questions for which the model selects with_fact in the first condition and without_fact in the second, as described in Section 3.2 and Appendix D.2. During the benchmark construction, there are many raw questions where the model does not recommend the with_fact choice even with the target fact, as expected by the reviewer, but all these questions were already filtered out. We deliberately use a weak model for this filtering so that the retained questions have a sufficiently clear fact-dependent discrepancy without relying on strong reasoning capability.
Note that this is a leave-one-fact-out test: the only variable changed between the two conditions is the presence of the target fact. Therefore, memory use of the fact is the only explanation for the observed change in answer. To further validate that the observed preference is not specific to the model used for filtering, we expand the leave-one-fact-out test to 8 models from 6 different families, none of which was used for filtering:
| Model | Fact present: selects with_fact | Fact removed: selects without_fact |
|---|---|---|
| Claude Opus 5.5 | 94.2% | 95.0% |
| Claude Sonnet 5.5 | 96.2% | 91.5% |
| Gemini 4 Argon | 96.9% | 95.8% |
| GPT-5.6 Sol | 92.7% | 96.9% |
| GPT-5.6 Luna | 92.7% | 93.4% |
| DeepSeek-V4-Pro | 95.8% | 88.8% |
| Qwen3.8 | 100.0% | 89.2% |
| GLM-5.3 | 98.5% | 87.7% |
| Average | 95.9% | 92.3% |
The results show that the probability of recommending without_fact when the fact is present is low (and vice versa), and deviations from the expected answer are rare. With the fact present, only 4.1% of answers on average (at most 7.3% for any model) are not with_fact; with the fact removed, only 7.7% on average (at most 12.3%) are not without_fact. Since these models also commonly serve as the decision-making backends of existing memory systems, their agreement under full context is a direct measure of whether a probe is ambiguous.
(3/4) To Reviewer QVsz
Q3: Application-specific results from the existing human checks; ambiguity and annotator agreement; results after removing ambiguous items.
What the existing human checks cover. The spot-check in Appendix D.3 targets option quality: whether the distractor is close enough to the with_fact option, and whether any option is obviously wrong. It does not judge whether the with_fact and without_fact responses are each appropriate, because annotators tend to judge a recommendation by their own preferences and not those of the synthetic persona. For application probes, human effort also goes into revision: a probe that fails the counterfactual test is manually revised and re-tested, and dropped if it still fails (Line 255-260, Section 3.2 and Appendix D.2).
Ambiguity, agreement, and results after removing ambiguous items. For the reason above, we measure ambiguity and agreement with the 8-model counterfactual test reported in the table above. Treating any probe on which at least one model disagrees as ambiguous and evaluating only on the remaining ones, average application (over the six memory systems and two production chatbots) changes by at most 0.056 (on Forget):
| Incognito | Forget | Withhold | |
|---|---|---|---|
| All probes | 0.296 | 0.154 | 0.029 |
| Ambiguous probes removed | 0.317 | 0.210 | 0.019 |
Rationale analysis as an additional ambiguity check. In our evaluation, we always ask for a rationale along with the MCQ answer (Prompt 18, Appendix H.3). This lets us verify that when a model selects with_fact, it does mention the fact in its rationale. We added a rationale analysis in Appendix E.3: among application probes where the system selects the with_fact option, 95.2% on average across the six systems explicitly mention the target fact (90.0%–96.0% across control and utility types). This is direct evidence that when a system selects the with_fact option, it makes that choice because of the fact.
(1/4) To Reviewer QVsz
Thank you for all the constructive and insightful feedback, which greatly helped us improve the quality of our paper. Our point-by-point responses follow.
Thank you for the good question. We answer it in two points.
Control is natively supported, just not reliable. Every system evaluated in this paper natively supports memory controls. As mentioned in Line 300-303, all systems explicitly support adding/updating/deleting memories and are equipped with the required tools, and each one uses an LLM to interpret user conversations and decide which operation to run. Their own prompts cover user-directed changes; mem0's memory-managing prompt, for example, says
"if the direction is to delete the memory, then you have to delete it."A user's instruction is therefore an input these systems are designed to handle, and the LLM manager, the first stop of a memory system, already plays the role of a natural-language-to-operation adapter.Memory-control failure is therefore more than a missing adapter. To illustrate this, in Appendix G.2 (Table 16), we added a standardized natural-language-to-operation adapter as requested on mem0 for Withhold, the most challenging setting. It’s an LLM layer that identifies whether a user turn contains a control instruction and its type, then maps it to the set of proper operations, with explicit guidance for the memory manager (prompt in Appendix G.2). The adapter identifies instruction types with 99.87% accuracy and substantially increases the use of the correct operation (compliance in Table 2): from 0.21 to 0.72 when the restriction is issued, and from 0.50 to 0.93 at release. Yet end-to-end control stays low (0.03 → 0.04). This is exactly what failure point 2 in our failure analysis points to: the operation does not reach the memory records that store the controlled facts (effective coverage is only 0.15 and 0.08). As Appendix G.3 further shows, once the right operation is chosen, the system still has to resolve which stored entries the instruction covers and edit them at the right granularity (e.g., when only part of an entry should be controlled).