paper-with-me

홈 › Papers

Below-Chance Blindness: Prompted Underperformance in Small LLMs Produces Positional Bias Rather than Answer Avoidance

2026-04-28 · Jon-Paul Cacioli arxiv

Detecting sandbagging--the deliberate underperformance on capability evaluations--is an open problem in AI safety. We tested whether symptom validity testing (SVT) logic from clinical malingering detection could identify sandbagging through below-chance performance (BCB) on forced-choice items. In a pre-registered pilot at the 7-9 billion parameter instruction-tuned scale (3 models, 4 MMLU-Pro domains, 4 conditions, 500 items per cell, 24,000 total trials), the plausibility gate failed. Zero of 12 model-domain cells showed significant below-chance performance under sandbagging instruction. Exploratory analyses revealed three qualitatively distinct failure modes. Qwen-2.5-7B and Phi-3.5-mini largely ignored the sandbagging instruction, with 62-88% response identity with the honest baseline. Llama-3-8B complied substantially but implemented underperformance as a positional heuristic, collapsing its response distribution onto middle-alphabet options (E at 31.8%, F at 26.1%) regardless of where the correct answer fell. This produced accuracy boosts of up to 33 percentage points when the correct answer coincidentally occupied the model's preferred position. An explicit anti-task instruction ("pick the least likely answer") drove two of three models below chance, with accuracy as low as 0.024. The capability for answer-aware avoidance therefore exists but is not activated by "deliberately underperform." BCB did not fail as a logical marker of answer-aware avoidance. It was not observed in this regime because the model showing the largest behavioural shift exhibited behaviour consistent with a position-dominant response policy rather than content-aware answer avoidance. We propose that positional-distribution shift may be a more effective behavioural signature than below-chance accuracy for detecting prompted underperformance at this model scale.

📄 PDF Abstract BibTeX arXiv:2604.25249

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Causal Transformers Perform Below Chance on Recursive Nested Constructions, Unlike Humans

2021-10-14 · Yair Lakretz, Théo Desbordes, Dieuwke Hupkes, Stanislas Dehaene

Recursive processing is considered a hallmark of human linguistic abilities. A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance le…

Large Language Models Pass the Turing Test

2025-03-31 · Cameron R. Jones, Benjamin K. Bergen

We evaluated 4 systems (ELIZA, GPT-4o, LLaMa-3.1-405B, and GPT-4.5) in two randomised, controlled, and pre-registered Turing tests on independent populations. Participants had 5 minute conversations simultaneously with a…

Can Transformers Process Recursive Nested Constructions, Like Humans?

2022-10-01 · COLING 2022 10 · Yair Lakretz, Théo Desbordes, Dieuwke Hupkes, Stanislas Dehaene

Recursive processing is considered a hallmark of human linguistic abilities. A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance le…

Why Indexing Works

2015-10-13 · J. B. Heaton, N. G. Polson, J. H. Witte

We develop a simple stock selection model to explain why active equity managers tend to underperform a benchmark index. We motivate our model with the empirical observation that the best performing stocks in a broad mark…

Management

Heterogeneity in Formal Linguistic Competence of Language Models: Is Data the Real Bottleneck?

2026-04-20 · H S V N S Kowndinya Renduchintala, Sumit Bhatia arxiv

Large Language Models (LLMs) exhibit a puzzling disparity in their formal linguistic competence: while they learn some linguistic phenomena with near-perfect mastery, they often perform below chance on others, even after…

Data Augmentation