Letting AI pick the right word meaning—no hand labels needed

Kari Jaaskelainen

21 Nov 2025 — 1 min read

Words often have many meanings. Choosing the right one in context—"bank" of a river or a lender?—is a classic AI challenge.

A new approach by Kexin Zhao and Ken Forbus blends symbolic understanding with modern language models. Here’s how it works:

A symbolic system lists possible meanings for a word.
Each meaning is rewritten as a clear, natural-language option.
An LLM is asked which option best fits the sentence.
The chosen meaning feeds back into the symbolic system for richer reasoning.

Why this matters: It avoids costly hand-labeled training data and goes beyond coarse labels (like WordNet frames) to support deeper knowledge bases (e.g., OpenCyc). In tests against human-annotated answers, the method proved effective.

Paper: Integrating Symbolic Natural Language Understanding and Language Models for Word Sense Disambiguation
Authors: Kexin Zhao, Ken Forbus
Link: https://arxiv.org/abs/2511.16577v1

Paper: https://arxiv.org/abs/2511.16577v1

Register: https://www.AiFeta.com

#AI #NLP #LLM #WordSenseDisambiguation #SymbolicAI #KnowledgeGraphs #NLU #Research

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A