Natural Language Decompositions of Implicit Content Enable Better Text Representations

Alexander Hoyle, Rupak Sarkar, Pranav Goel, Philip Resnik
5/23/2023
cs.CL

No official code found. Best implementation: ahoho/inferential-decompositions (9 stars, last commit 2024-02-08).

Abstract

When people interpret text, they rely on inferences that go beyond the observed language itself. Inspired by this observation, we introduce a method for the analysis of text that takes implicitly communicated content explicitly into account. We use a large language model to produce sets of propositions that are inferentially related to the text that has been observed, then validate the plausibility of the generated content via human judgments. Incorporating these explicit representations of implicit content proves useful in multiple problem settings that involve the human interpretation of utterances: assessing the similarity of arguments, making sense of a body of opinion data, and modeling legislative behavior. Our results suggest that modeling the meanings behind observed language, rather than the literal text alone, is a valuable direction for NLP and particularly its applications to social science.

View on arXivView PDF

Code Implementations(1)

ahoho/inferential-decompositionsCommunity100%
91Shell, PythonOct 18, 20232 years ago

Similar Papers

Interpretation modeling: Social grounding of sentences by reasoning over their implicit moral judgments

85% match2023

Interpreting Pretrained Language Models via Concept Bottlenecks

84% match1 repo52023

POSQA: Probe the World Models of LLMs with Size Comparisons

83% match1 repo42023

A Design-based Solution for Causal Inference with Text: Can a Language Model Be Too Large?

83% match2025

Inspecting and Editing Knowledge Representations in Language Models

83% match1 repo1192023

The Moral Turing Test: Evaluating Human-LLM Alignment in Moral Decision-Making

83% match2024

Cite this paper

@article{hoyle2023natural,
  title  = {Natural Language Decompositions of Implicit Content Enable Better Text Representations},
  author = {Alexander Hoyle and Rupak Sarkar and Pranav Goel and Philip Resnik},
  year   = {2023},
  eprint = {2305.14583},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2305.14583v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2305.14583.svg)](https://codeofpaper.com/paper/2305.14583)

Discussion