Pith. sign in

Robust separation of true/false for affirmative & negated statements; tG generalizes well

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

representative citing papers

Can LLMs Lie? Investigation beyond Hallucination

cs.LG · 2025-09-03 · conditional · novelty 6.0

The paper localizes LLM lying to sparse attention heads and chat-template 'dummy tokens', and shows steering vectors can modulate deception, but the evidence is weakened by selection and small samples.

citing papers explorer

Showing 1 of 1 citing paper.

  • Can LLMs Lie? Investigation beyond Hallucination cs.LG · 2025-09-03 · conditional · none · ref 37

    The paper localizes LLM lying to sparse attention heads and chat-template 'dummy tokens', and shows steering vectors can modulate deception, but the evidence is weakened by selection and small samples.