Challenge: Analogy-making is a central to human cognition, allowing us to abstract information and understand novel situations in terms of familiar ones.
Approach: They propose a pipeline to generate paragraph-based analogies using large language models and large language distractors.
Outcome: The proposed pipeline outperforms existing models in binary and multiple-choice settings and shows that humans outperformed the best models after a light supervision.

Similar Papers

AnaloBench: Benchmarking the Identification of Abstract and Long-context Analogies (2024.emnlp-main)

Copied to clipboard

Challenge: Analogical reasoning is an important part of human communication, says a new study . a benchmark to determine analogical reasoning ability in language models is needed .
Approach: They propose to benchmark analogical reasoning ability in language models by collecting 340 analogies from human writings.
Outcome: The proposed benchmark aims to determine analogical reasoning ability in language models.
Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes (2022.emnlp-main)

Copied to clipboard

Challenge: Analogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference – abilities that current AI systems lack.
Approach: They propose an interpretable, scalable algorithm that extracts analogies from a pair of natural language procedural texts and finds a mapping between the different domains based on relational similarity.
Outcome: The proposed algorithm can extract analogies from a large dataset and achieve 79% precision.
Scientific and Creative Analogies in Pretrained Language Models (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing analogy datasets focus on a limited set of analogical relations with a high similarity of the two domains between which the analogy holds.
Approach: They propose a dataset that encodes analogy in pretrained language models . they use a system that maps attributes and relational structures across dissimilar domains .
Outcome: The proposed dataset shows that state-of-the-art models achieve low performance on analogy tasks .
ANALOGYKB: Unlocking Analogical Reasoning of Language Models with A Million-scale Knowledge Base (2024.acl-long)

Copied to clipboard

Challenge: ANALOGYKB is a million-scale analogy knowledge base based on existing knowledge graphs (KGs) based upon relational knowledge triples, we can discover new analogies using the corresponding relations between concepts.
Approach: They propose a million-scale analogy knowledge base derived from existing knowledge graphs (KGs) ANALOGYKB identifies analogies of the same relations and analogies from analogous relations .
Outcome: The proposed model enables both smaller LMs and LLMs to gain better analogical reasoning capabilities.
Textagon: Boosting Language Models with Theory-guided Parallel Representations (2025.acl-demo)

Copied to clipboard

Challenge: Pretrained language models do not account for the wide variety of available expert-generated language resources and lexicons that explicitly encode linguistic/domain knowledge.
Approach: They propose a Python package for generating parallel representations for text based on predefined lexicons and selecting representations that provide the most information.
Outcome: The proposed model can generate parallel representations of text based on predefined lexicons and select representations that provide the most information.
MGAD: Multilingual Generation of Analogy Datasets (L18-1)

Copied to clipboard

Challenge: Existing methods for word embedding evaluation are computationally expensive and task-specific.
Approach: They propose a minimally supervised method for generating word embedding evaluation datasets for a large number of languages using existing dependency treebanks and parsers.
Outcome: The proposed method evaluates three popular word embedding algorithms against these datasets and shows that their performance varies between syntactic categories.
FAME: Flexible, Scalable Analogy Mappings Engine (2023.emnlp-main)

Copied to clipboard

Challenge: Most work on computational analogy relies heavily on complex, manually crafted input.
Approach: They propose to use commonsense representations to identify mappings between entities and use them to interpret their output.
Outcome: The proposed model outperforms human models on large analogy problems and outperfies human predictions.
Tools for The Production of Analogical Grids and a Resource of N-gram Analogical Grids in 11 Languages (L18-1)

Copied to clipboard

Challenge: a Python module implements several previously presented algorithms to build analogical grids from words contained in a corpus.
Approach: They propose to release a Python module which implements several previously presented algorithms to build analogical grids from words contained in a corpus.
Outcome: The tools were built on vocabularies contained in 1,000 lines of the 11 different language versions of the Europarl corpus v.3 and are language-independent, allowing their use with any language and any writing system.
KnowledgePrompts: Exploring the Abilities of Large Language Models to Solve Proportional Analogies via Knowledge-Enhanced Prompting (2025.coling-main)

Copied to clipboard

Challenge: Proportional analogies are used to assess linguistic and cognitive abilities.
Approach: They propose a dataset for proportional analogy completion and evaluate its performance in large-scale learning environments.
Outcome: The proposed model achieves 55% accuracy in knowledge-enhanced prompts.
StoryAnalogy: Deriving Story-level Analogies from Large Language Models to Unlock Analogical Understanding (2023.emnlp-main)

Copied to clipboard

Challenge: Analogy-making between narratives is crucial for human reasoning . despite its importance, there has been limited research on story analogies .
Approach: They construct a large-scale story-level analogy corpus with 24K story pairs . they find that the tasks are incredibly difficult for large language models such as ChatGPT .
Outcome: The proposed corpus contains 24K story pairs from diverse domains with human annotations on two similarities from the extended Structure-Mapping Theory.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations