Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yingji, Valentino, Marco, Carvalho, Danilo S., Freitas, André
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2506.19418
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909833577365504
author Zhang, Yingji
Valentino, Marco
Carvalho, Danilo S.
Freitas, André
author_facet Zhang, Yingji
Valentino, Marco
Carvalho, Danilo S.
Freitas, André
contents Incorporating explicit reasoning rules within the latent space of language models (LMs) offers a promising pathway to enhance generalisation, interpretability, and controllability. While current Transformer-based language models have shown strong performance on Natural Language Inference (NLI) tasks, they often rely on memorisation rather than rule-based inference. This work investigates how reasoning rules can be explicitly embedded and memorised within the LMs through Language Variational Autoencoders (VAEs). We propose a complete pipeline for learning reasoning rules within Transformer-based language VAEs. This pipeline encompasses three rule-based reasoning tasks, a supporting theoretical framework, and a practical end-to-end architecture. The experiment illustrates the following findings: Disentangled reasoning: Under explicit signal supervision, reasoning rules - viewed as functional mappings - can be disentangled within the encoder's parametric space. This separation results in distinct clustering of rules in the output feature space. Prior knowledge injection: injecting reasoning information into the Query enables the model to more effectively retrieve the stored value Value from memory based on Key. This approach offers a simple method for integrating prior knowledge into decoder-only language models. Performance bottleneck: In mathematical reasoning tasks using Qwen2.5(0.5B), increasing sample count doesn't improve performance beyond a point. Moreover, ffn layers are better than attention layers at preserving the separation of reasoning rules in the model's parameters.
format Preprint
id arxiv_https___arxiv_org_abs_2506_19418
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
Zhang, Yingji
Valentino, Marco
Carvalho, Danilo S.
Freitas, André
Computation and Language
Incorporating explicit reasoning rules within the latent space of language models (LMs) offers a promising pathway to enhance generalisation, interpretability, and controllability. While current Transformer-based language models have shown strong performance on Natural Language Inference (NLI) tasks, they often rely on memorisation rather than rule-based inference. This work investigates how reasoning rules can be explicitly embedded and memorised within the LMs through Language Variational Autoencoders (VAEs). We propose a complete pipeline for learning reasoning rules within Transformer-based language VAEs. This pipeline encompasses three rule-based reasoning tasks, a supporting theoretical framework, and a practical end-to-end architecture. The experiment illustrates the following findings: Disentangled reasoning: Under explicit signal supervision, reasoning rules - viewed as functional mappings - can be disentangled within the encoder's parametric space. This separation results in distinct clustering of rules in the output feature space. Prior knowledge injection: injecting reasoning information into the Query enables the model to more effectively retrieve the stored value Value from memory based on Key. This approach offers a simple method for integrating prior knowledge into decoder-only language models. Performance bottleneck: In mathematical reasoning tasks using Qwen2.5(0.5B), increasing sample count doesn't improve performance beyond a point. Moreover, ffn layers are better than attention layers at preserving the separation of reasoning rules in the model's parameters.
title Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study
topic Computation and Language
url https://arxiv.org/abs/2506.19418