Ananth Agarwal — accepted AI-conference papers

2025

Mechanisms vs. Outcomes: Probing for Syntax Fails to Explain Performance on Targeted Syntactic Evaluations

Ananth Agarwal, Jasper Jian, Christopher D Manning, Shikhar Murty

EMNLP 2025

Large Language Models (LLMs) exhibit a robust mastery of syntax when processing and generating text. While this suggests internalized understanding of hierarchical syntax and dependency relations, the precise mechanism by which they represent syntactic structure is an open area within interpretabili

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Enhancing Self-Consistency and Performance of Pre-Trained Language Models through Natural Language Inference

Eric Mitchell, Joseph Noh, Siyan Li, Will Armstrong, Ananth Agarwal, Patrick Liu +2

EMNLP 2022main

While large pre-trained language models are powerful, their predictions often lack logical consistency across test inputs. For example, a state-of-the-art Macaw question-answering (QA) model answers Yes to Is a sparrow a bird? and Does a bird have feet? but answers No to…

Cited by 47 Source ↗PDF ↗Scholar ↗