Pith. sign in

Leveraging Large Language Models for Learning Complex Legal Concepts through Storytelling , booktitle =

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

1 Pith paper citing it

fields

cs.LG 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Training Large Language Models for Self-Explanation Faithfulness

cs.LG · 2026-07-23 · conditional · novelty 6.0

RL fine-tuning with a counterfactual mention/influence reward raises LLM self-explanation faithfulness (Phi-CCT) from near zero to ~0.66 in-distribution for two 8B models, with partial transfer to held-out tasks.

citing papers explorer

Showing 1 of 1 citing paper.

  • Training Large Language Models for Self-Explanation Faithfulness cs.LG · 2026-07-23 · conditional · none · ref 43

    RL fine-tuning with a counterfactual mention/influence reward raises LLM self-explanation faithfulness (Phi-CCT) from near zero to ~0.66 in-distribution for two 8B models, with partial transfer to held-out tasks.