Generating Edit-Inducing Questions for AI Research Manuscripts

Can This LLM Annotate My Data? Estimating Zero-Shot LLM Performance

It is found that it is possible to predict LLM performance - to a certain degree - and that contrary to other work which highlights the usefulness of LLM verbalizations of self-confidence, internal log-probabilities are the most predictive signal.

ReGround: Grounding Reviewer Comments in Multimodal Evidence

ReGround is introduced, a large-scale dataset for reviewer comment grounding that links 10,267 reviewer comments to 16,274 evidence in the original anonymous submission of 3,656 papers and exposes grounding reviewer comments as a difficult and practically important problem for scientific document understanding.

Document Summarization for AI-based Post-Editing

It is suggested that summary specificity and actionability, rather than the mere addition of context, determine whether document-level information benefits post-editing.

LLM-based Defense Against Adversarial Abstracts in ML/AI Conference Reviewer Assignments

GRASP and GRISP for Question Answering over Wikidata

From Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular Classification

While Large Language Models (LLMs) possess rich world knowledge and impressive generalization capabilities, their direct application to tabular data classification is hindered by high inference costs and limited interpretability. In contrast, decision trees are fast and transparent but often underperform in low-data re...