iiinova — where your digital self keeps evolving

Weiqiu You

@youweiqiu.bsky.social

PhD Student at University of Pennsylvania CIS in ML and explainable AI. | Former MS @UMassCS, Intern @OIST @IBM @USC_ISI | She/her fallcat.github.io

Posts Replies Media

Weiqiu You @youweiqiu.bsky.social · 04/11/2025

Huge thanks to all my collaborators @antonxue.bsky.social, @shreyahavaldar.bsky.social , @deliprao.bsky.social , @helenjin.bsky.social, Chris Callison-Burch, @riceric22.bsky.social

000

Weiqiu You @youweiqiu.bsky.social · 04/11/2025

LLMs often make reasoning errors. However, current LLM error detection methods often fail when earlier errors corrupt downstream judgments. We introduce Autoregressive Reasoning Entailment Stability (ARES), an framework for measuring reasoning soundness with stability guarantees.

100

Weiqiu You @youweiqiu.bsky.social · 04/11/2025

I'll be presenting our work "Probabilistic Soundness Guarantees in LLM Reasoning Chains" at EMNLP 2025 Today (Nov 5) Hall C 14:30-16:00 802-Main Blog: debugml.github.io/ares Paper: arxiv.org/abs/2507.12948 Code: github.com/fallcat/ares

110

Weiqiu You @youweiqiu.bsky.social · 19/07/2025

Joint works with @profericwong.bsky.social @antonxue.bsky.social @shreyahavaldar.bsky.social @helenjin.bsky.social @deliprao.bsky.social Chris Callison-Burch, Helen Qu, Marco Gatti, Bhuvnesh Jain

000

Weiqiu You @youweiqiu.bsky.social · 19/07/2025

See our posters at Actionable Interpretability workshop East Ballroom A Probabilistic Soundness Guarantees in LLM Reasoning Chains arxiv.org/abs/2507.12948 10:40-11:40am Sum-of-Parts: Self-Attributing Neural Networks with End-to-End Learning of Feature Group debugml.github.io/sum-of-parts 1-2pm

130