Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer
Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and correctly when it is present. We test this assumption by introducing a semantic notion of answer availability that aggregates token-level variants expressing the same answer concept, and asks whether the correct concept is already available at the moment the model commits to an answer. Across Qwen and Llama models from 0.8B to 72B in both Instruct and Base variants, 16-47% of Instruct hallucinations occur with substantial probability mass already on the correct concept, and the rate rises monotonically with scale. Comparing such failures against correct generations with matched semantic support, the distinguishing factor is not whether the correct concept is represented, but how its probability is distributed: correct generations concentrate mass on a single surface form, hallucinations disperse it across alternatives. The same sharpening asymmetry extends across multi-token generation and is detectable in pre-generation hidden states. Together, these results identify a single mechanism: instruction tuning sharpens answer commitment with scale, making helpfulness and confident hallucination two consequences of the same underlying disposition.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
The Wrong Kind of Right: Quantifying and Localizing Misfired Alignment in LLMs
Warning: This paper studies stereotypes and biases, and contains potentially disturbing examples, used for illustration purposes only. Our findings should not be interpreted as an argument against alignment. Instead, thi…
Whitening Reveals Cluster Commitment as the Geometric Separator of Hallucination Types
A geometric hallucination taxonomy distinguishes three failure types -- center-drift (Type~1), wrong-well convergence (Type~2), and coverage gaps (Type~3) -- by their signatures in embedding cluster space. Prior work fou…
Credal Large Language Models for Semantic Commitment under Uncertainty
Large language models (LLMs) often produce fluent but incorrect answers with unwarranted confidence. A central limitation is that standard LLMs represent uncertainty through a single predictive distribution, conflating e…
Structural Rigidity and the 57-Token Predictive Window: A Physical Framework for Inference-Layer Governability in Large Language Models
Current AI safety relies on behavioral monitoring and post-training alignment, yet empirical measurement shows these approaches produce no detectable pre-commitment signal in a majority of instruction-tuned models tested…
From Architecture to Output: Structural Origins of Hallucination in Large Language Models and the Amplifying Role of Data
Large language models produce fluent, confident, factually wrong output. Existing taxonomies classify these failures by output type -- intrinsic versus extrinsic, faithfulness versus factuality -- but say nothing about w…