Showing cs.CLShow all
2 papers · 1 filter
cs.CL2026
Correctness Is a Direction: Geometric Answer Selection in Language Models
Marcus Armstrong, Navid Ayoobi, Pradham Mummaleti +2
Answer correctness is encoded as a recoverable geometric direction in the hidden states of language models. We show that the mean displacement from incorrect to correct answer repr…
cs.CL2026
Say Anything but This: When Tokenizer Betrays Reasoning in LLMs
Navid Ayoobi, Marcus I Armstrong, Arjun Mukherjee
Large language models (LLMs) reason over discrete token ID sequences, yet modern subword tokenizers routinely produce non-unique encodings: multiple token ID sequences can detokeni…