pith. sign in

Improved supervised fine-tuning for large language models to mitigate catastrophic forgetting

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.AI 1 cs.LG 1

years

2026 1 2025 1

verdicts

UNVERDICTED 2

representative citing papers

Emergent Slow Thinking in LLMs as Inverse Tree Freezing

cs.AI · 2025-09-28 · unverdicted · novelty 6.0

RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.

citing papers explorer

Showing 2 of 2 citing papers.

  • Crafting Reversible SFT Behaviors in Large Language Models cs.LG · 2026-05-07 · unverdicted · none · ref 11

    LCDD creates sparse carriers for SFT behaviors that SFT-Eraser can reverse, with ablations showing the sparse structure enables causal control.

  • Emergent Slow Thinking in LLMs as Inverse Tree Freezing cs.AI · 2025-09-28 · unverdicted · none · ref 9

    RLVR drives a concept network in LLMs through nucleation and freezing into inverse trees that support slow thinking, and intervening with brief SFT at peak frustration outperforms standard RLVR while post-freeze SFT causes forgetting.