Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMs

arXiv:2609.39572 · cs.CL · Submitted 2026-09-30 · Read on arXiv

cs.CL

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/mregneri/ambiguity_abstraction_llms

Terminology

Abstraction — 18× in this paper · explained in 1 episode
Accuracy — 18× in this paper · explained in 1 episode
Cosine Similarity — 7× in this paper · explained in 3 episodes
Embeddings — 4× in this paper · explained in 2 episodes
Transformer — 4× in this paper · explained in 2 episodes
Benchmark — 3× in this paper · explained in 2 episodes
Transformer Models — 3× in this paper · explained in 2 episodes
Alignment — 2× in this paper · explained in 1 episode
Interpretability — 2× in this paper · explained in 15 episodes
Perplexity — 2× in this paper · explained in 3 episodes
Ablation — 1× in this paper · explained in 1 episode
Attention Mechanism — 1× in this paper · explained in 3 episodes
Core — 1× in this paper · explained in 2 episodes
Downstream Tasks — 1× in this paper · explained in 2 episodes
Generalizability — 1× in this paper · explained in 6 episodes
Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
Mechanistic interpretability — 1× in this paper · explained in 2 episodes
Tokenization — 1× in this paper · explained in 2 episodes
Von Neumann Entropy — 1× in this paper

Sources

TinyStories: How Small Can Language Models Be and Still Speak Coherent English?

Related papers