AINov 8, 2023

Pragmatic Reasoning Unlocks Quantifier Semantics for Foundation Models

arXiv:2311.04659v1131 citationsh-index: 6
Originality Incremental advance
AI Analysis

This addresses a specific challenge in natural language understanding for AI researchers, but it is incremental as it builds on existing methods like Rational Speech Acts.

The paper tackled the problem of whether foundation models can interpret generalized quantifiers by binding them to percentage scopes, and found that a pragmatic reasoning framework (PRESQUE) improved prediction accuracy by 20% over a literal baseline without extra training.

Generalized quantifiers (e.g., few, most) are used to indicate the proportions predicates are satisfied (for example, some apples are red). One way to interpret quantifier semantics is to explicitly bind these satisfactions with percentage scopes (e.g., 30%-40% of apples are red). This approach can be helpful for tasks like logic formalization and surface-form quantitative reasoning (Gordon and Schubert, 2010; Roy et al., 2015). However, it remains unclear if recent foundation models possess this ability, as they lack direct training signals. To explore this, we introduce QuRe, a crowd-sourced dataset of human-annotated generalized quantifiers in Wikipedia sentences featuring percentage-equipped predicates. We explore quantifier comprehension in language models using PRESQUE, a framework that combines natural language inference and the Rational Speech Acts framework. Experimental results on the HVD dataset and QuRe illustrate that PRESQUE, employing pragmatic reasoning, performs 20% better than a literal reasoning baseline when predicting quantifier percentage scopes, with no additional training required.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes