pith. sign in

ACPBench: Reasoning about Action, Change, and Planning

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

2 Pith papers citing it

fields

cs.AI 1 cs.CL 1

years

2026 2

representative citing papers

When AI Says It Feels

cs.AI · 2026-06-04 · unverdicted · novelty 5.0

LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.

citing papers explorer

Showing 2 of 2 citing papers.

  • HalluWorld: A Controlled Benchmark for Hallucination via Reference World Models cs.CL · 2026-05-19 · conditional · none · ref 30

    HalluWorld is a controlled benchmark using explicit reference world models to automatically label and disentangle hallucinations in LLMs across synthetic environments with varying complexity and observability.

  • When AI Says It Feels cs.AI · 2026-06-04 · unverdicted · none · ref 33

    LLMs trained via rubric-based self-rewarding RL with GRPO enhanced feeling expression and sycophancy robustness but degraded truthful QA performance.