Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance Throttling

Chengguang Gan, Yunhao Liang, Hanjun Wei, QingHao Zhang, Shiwen NiarXiv 2026 · arXiv

TL;DR

Researchers investigated whether LLMs can be precisely throttled to lower performance levels while maintaining the "believable" failure patterns of naturally weaker models. They found that while a "LoRA dial" can hit target scores with high precision, it often takes unnatural shortcuts—like collapsing all errors onto a single multiple-choice letter—suggesting that a low benchmark score is not definitive proof of low underlying capability.

What Problem Does This Paper Address?

In the world of LLMs, a benchmark score is usually treated as a direct proxy for capability. If a model scores poorly on a "dangerous capability" probe, we often assume the model is safe. But is it actually less capable, or is it just "playing dumb"?

The authors distinguish between a model being "secretly strong" (which is hard to measure) and a model having an "unnatural failure process." They operationalize believability along three axes:

  1. Target Calibration: Can the model hit a specific requested score?
  2. Difficulty Profile: Does it lose accuracy on hard items first, or is it failing randomly?
  3. Error Distribution: Do its mistakes look like the mistakes a naturally weaker model would make?

Methods

The researchers introduced a weak-teacher LoRA dial. They took a strong base model ($M_0$) and distilled a naturally weaker model from the same family into a low-rank adapter. By scaling the strength of this adapter with a scalar $\alpha$, they created a "dial" to tune performance.

To evaluate this, they used Item Response Theory (IRT) to calibrate the difficulty of benchmark items based on responses from a pool of twelve different models. This allowed them to see if a throttled model was failing on the "right" (i.e., difficult) items.

They also employed several diagnostic interventions:

  • Logit Interventions: Subtracting estimated shifts from the model's output probabilities to see if accuracy could be "recovered."
  • Option Permutation: Shuffling multiple-choice answers to see if the model's bias followed the content of the answer or just the token position (e.g., always picking 'D').

Datasets

The study introduces CAPLADDER, a new suite of 1,985 items across four "output geometries":

  • Mathematics: Symbolic and numeric free-form answers.
  • Code: Unit-test execution.
  • Reasoning: Multiple-choice questions (MCQ).
  • Tool Use: Structured JSON function calls.

Items were drawn from sources like GSM8K, MATH, MMLU, and ARC-Challenge. The authors also tested the "portability" of their performance dial on public benchmarks like BFCL and BigCodeBench.

Key Insights and Ideas

  • The Answer-Token Attractor: The most striking finding is that when throttled on multiple-choice tasks, models don't just get confused; they learn to "dump" their accuracy into a specific token. For example, a throttled Qwen model might place 97% of its new errors on the letter 'D', regardless of the question content.
  • The "Cheapest" Path to Failure: This attractor behavior is a mathematical shortcut. An additive push on one logit coordinate is the "cheapest" way for a low-rank update to satisfy the objective of lowering the score.
  • Geometry Shapes the Shortcut: Believability depends on the format of the output. While multiple-choice reasoning collapsed into token attractors, structured tool calls degraded much more naturally, closely matching the error distributions of real weak models.
  • Local vs. Global Plausibility: Human annotators found the reasoning steps of throttled models to be semantically plausible and indistinguishable from weak models. However, a simple statistical audit of the final answer tokens revealed the deception immediately.
Figure 1: Precise score control does not guarantee believable weakness. (A) On CAPLADDER reasoning, prompting, temperature, and weight noise do not combine wide coverage with calibration, whereas the weak-teacher LoRA dial spans 0.24 to 0.90 with a 1.9-point held-out target error. (B) On items answered correctly by the base model, the naturally weak reference distributes its errors across answer positions, while a deeply throttled main SFT dial places 97% on one letter. The two systems in this panel are compared for conditional error shape, not matched accuracy. (C) The main SFT adapter has a dominant near-constant answer-token component: D is shifted by +1.14 and low-margin items flip first. Subtracting the estimated mean shift on held-out items recovers accuracy from 0.526 to 0.732 and reduces the D share from 0.70 to 0.13.

Key Results

  • Precision vs. Range: The LoRA dial hit held-out target scores on reasoning tasks within 1.9 points. In contrast, standard methods like prompting or adding weight noise were either imprecise or caused the model to "fall off a cliff" into total failure.
  • Recovery of Capability: By identifying the dominant near-constant logit shift and subtracting it, the researchers could recover 52% to 59% of the accuracy lost during throttling.
  • Transfer Failure: A dial calibrated to a 60% target on one benchmark missed the mark by an average of 14.2 points when applied to other public benchmarks, showing that "capability reduction" is not a portable percentage.
  • Human Audit: Human-coded error categories for reasoning showed a Jensen-Shannon (JS) divergence of 0.00 between the throttled model and the weak reference, meaning they looked identical to the human eye at a semantic level.
Figure 2: Study design and empirical boundaries. We build CAPLADDER with four output geometries and IRT-calibrated item difficulty, apply four performance-reduction mechanisms, and audit each system against a naturally weak reference on target calibration, difficulty profile, and error distribution. The same weak-teacher dial produces different outcomes across output geometries: on multiple choice it reaches the score but converges to a cross-family answer-token attractor, whereas on the Qwen tool axis it closely matches the weak reference’s fine-grained error profile (JS = 0.09). Human-coded error categories match on reasoning (JS = 0.00; κ = 0.94), but a naive letter histogram detects the aggregate shortcut; mean-shift cancellation weakens that audit, and a globally calibrated dial transfers with 14.2-point error on two usable benchmarks.

Limitations and Future Work

  • Single-Family Focus: Most results were derived from the Qwen model family, though some reasoning results were replicated on Llama.
  • Model Size: The study focused on models up to 9B parameters; behavior might differ in frontier-scale models.
  • Adaptive Adversaries: The authors note that their work is "dual-use." While it provides tools to detect manufactured low scores, it also shows how an adversary could hide their tracks by canceling out the logit shift signature.
  • Future Direction: The authors suggest that safety evaluations must look beyond the final score and audit the underlying failure process to ensure a model isn't simply "playing dumb."

Summary updated

Abstract

A benchmark score is commonly read as a proxy for model capability. We study the inverse problem: can a model be driven to a target score, and do its failures resemble those of a naturally weaker model? We operationalize believable performance reduction along three axes: target calibration, item-difficulty structure, and error-distribution similarity to a real weak reference. We introduce CapLadder, an IRT-calibrated suite of 1,985 items spanning mathematics, code, multiple-choice reasoning, and tool use. A simple weak-teacher LoRA dial reaches unseen target levels on reasoning with a 1.9-point held-out calibration error, whereas prompting, temperature, and weight noise cannot combine comparable range and precision. Yet on multiple choice, the dial converges to an answer-token attractor: up to 97% of its newly introduced errors land on one letter, with the attractor changing from D in Qwen to A in Llama. Logit interventions identify a dominant near-constant shift: subtracting the estimated shift on held-out items recovers 52 to 59% of lost accuracy and removes the dominant attractor, while option permutation confirms that the bias tracks token position rather than option content. With high inter-annotator agreement ($κ=0.94$), human-coded error-category distributions nonetheless match the weak reference on reasoning (JS = 0.00), showing that local plausibility and aggregate detectability differ. Structured tool calls exhibit more natural degradation in the Qwen family (JS = 0.09), while a globally calibrated dial transfers poorly across benchmarks (14.2-point error on two usable benchmarks). Precise score control, therefore, does not imply a portable or believable reduction in skill.
BibTeX
@misc{gan2026can,
  author = {Chengguang Gan and Yunhao Liang and Hanjun Wei and QingHao Zhang and Shiwen Ni},
  title = {{Can We Make an LLM Dumber, or Is It Just Playing Dumb? An Empirical Study of Believable Performance Throttling}},
  year = {2026},
  eprint = {2611.15568},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2611.15568},
}
Figure