Author name cluster

André Freitas

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

1 author row

AAAI Conference 2026 Conference Paper

Learning to Disentangle Latent Reasoning Rules with Language VAEs: A Systematic Study

Yingji Zhang
Marco Valentino
Danilo Carvalho
André Freitas

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 explicit rule-based generalisation. This work investigates how human-interpretable reasoning rules can be explicitly encoded within LMs with the support of Language Variational Autoencoders (VAEs), as a mechanism for generative control. 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 rule-based constraints into the Query enables the model to more effectively retrieve the stored Value from memory based on Key. This approach offers a simple method for integrating prior knowledge into decoder-only language models. Moreover, we found that FFN layers are better than attention layers at preserving the separation of reasoning rules in the model's parameters.

PDF Details DOI

AAAI Conference 2026 Conference Paper

Mitigating Content Effects on Reasoning in Language Models Through Fine-Grained Activation Steering

Marco Valentino
Geonhee Kim
Dhairya Dalal
Zhixue Zhao
André Freitas

Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, where plausible arguments are incorrectly deemed logically valid or vice versa. This paper investigates how content biases on reasoning can be mitigated through activation steering, an inference-time technique that modulates internal activations. Specifically, after localising the layers responsible for formal and plausible inference, we investigate activation steering on a controlled syllogistic reasoning task, designed to disentangle formal validity from content plausibility. An extensive empirical analysis reveals that contrastive steering methods consistently support linear control over content biases. However, a static approach is insufficient to debias all the tested models. We then investigate how to control content effects by dynamically determining the steering parameters through fine-grained conditional methods. By introducing a novel kNN-based conditional approach (K-CAST), we demonstrate that conditional steering can effectively reduce biases on unresponsive models, achieving up to 15% absolute improvement in formal reasoning accuracy. Finally, we found that steering for content effects is robust to prompt variations, incurs minimal side effects on multilingual language modeling capabilities, and can partially generalize to different reasoning tasks. In practice, we demonstrate that activation-level interventions offer a scalable inference-time strategy for enhancing the robustness of LLMs, contributing towards more systematic and unbiased reasoning capabilities

PDF Details DOI

AAAI Conference 2025 Conference Paper

Controlling Equational Reasoning in Large Language Models with Prompt Interventions

Jordan Meadows
Marco Valentino
André Freitas

This paper investigates how hallucination rates in Large Language Models (LLMs) may be controlled via a symbolic data generation framework, exploring a fundamental relationship between the rate of certain mathematical errors and types of input intervention. Specifically, we systematically generate data for a derivation generation task using a symbolic engine, applying targeted interventions to prompts to perturb features of mathematical derivations such as the surface forms of symbols, equational tree structures, and mathematical context. We then evaluate the effect of prompt interventions across a range of LLMs including fine-tuned T5 models, GPT, and LLaMa-based models. Our experiments suggest that T5-Large can outperform the few-shot performance of GPT-4 on various evaluation sets generated via the framework. However, an extensive evaluation based on human analysis, template-based error detection, and text generation metrics reveals model weaknesses beyond what the reference-based metrics singularly describe. We use these results to tie characteristic distributional footprints of interventions to the human evaluation of LLM derivation quality, potentially leading to significant control over fine-grained mathematical capabilities of language models with respect to specific types of errors.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Inductive Learning of Logical Theories with LLMs: A Expressivity-graded Analysis

João Pedro Gandarela de Souza
Danilo Carvalho
André Freitas

This work presents a novel systematic methodology to analyse the capabilities and limitations of Large Language Models (LLMs) with feedback from a formal inference engine, on logic theory induction. The analysis is complexity-graded w.r.t. rule dependency structure, allowing quantification of specific inference challenges on LLM performance. Integrating LLMs with formal methods is a promising frontier in the Natural Language Processing field, as an important avenue for improving model inference control and explainability. In particular, inductive learning over complex sets of facts and rules, poses unique challenges for current autoregressive models, as they lack explicit symbolic grounding. While they can be complemented by formal systems, the properties delivered by LLMs regarding inductive learning, are not well understood and quantified. Empirical results indicate that the largest LLMs can achieve competitive results against a SOTA Inductive Logic Programming (ILP) system baseline, but also that tracking long predicate relationship chains is a more difficult obstacle than theory complexity for LLMs.

PDF Details DOI

AIJ Journal 2023 Journal Article

Assessing the communication gap between AI models and healthcare professionals: Explainability, utility and trust in AI-driven clinical decision-making

Oskar Wysocki
Jessica Katharine Davies
Markel Vigo
Anne Caroline Armstrong
Dónal Landers
Rebecca Lee
André Freitas

This paper contributes with a pragmatic evaluation framework for explainable Machine Learning (ML) models for clinical decision support. The study revealed a more nuanced role for ML explanation models, when these are pragmatically embedded in the clinical context. Despite the general positive attitude of healthcare professionals (HCPs) towards explanations as a safety and trust mechanism, for a significant set of participants there were negative effects associated with confirmation bias, accentuating model over-reliance and increased effort to interact with the model. Also, contradicting one of its main intended functions, standard explanatory models showed limited ability to support a critical understanding of the limitations of the model. However, we found new significant positive effects which repositions the role of explanations within a clinical context: these include reduction of automation bias, addressing ambiguous clinical cases (cases where HCPs were not certain about their decision) and support of less experienced HCPs in the acquisition of new domain knowledge.

Details DOI

AAAI Conference 2022 Conference Paper

Hybrid Autoregressive Inference for Scalable Multi-Hop Explanation Regeneration

Marco Valentino
Mokanarangan Thayaparan
Deborah Ferreira
André Freitas

Regenerating natural language explanations in the scientific domain has been proposed as a benchmark to evaluate complex multi-hop and explainable inference. In this context, large language models can achieve state-of-the-art performance when employed as cross-encoder architectures and fine-tuned on human-annotated explanations. However, while much attention has been devoted to the quality of the explanations, the problem of performing inference efficiently is largely under studied. Cross-encoders, in fact, are intrinsically not scalable, possessing limited applicability to realworld scenarios that require inference on massive facts banks. To enable complex multi-hop reasoning at scale, this paper focuses on bi-encoder architectures, investigating the problem of scientific explanation regeneration at the intersection of dense and sparse models. Specifically, we present SCAR (for Scalable Autoregressive Inference), a hybrid framework that iteratively combines a Transformer-based bi-encoder with a sparse model of explanatory power, designed to leverage explicit inference patterns in the explanations. Our experiments demonstrate that the hybrid framework significantly outperforms previous sparse models, achieving performance comparable with that of state-of-the-art cross-encoders while being ≈ 50 times faster and scalable to corpora of millions of facts. Further analyses on semantic drift and multi-hop question answering reveal that the proposed hybridisation boosts the quality of the most challenging explanations, contributing to improved performance on downstream inference tasks.

PDF Details

AAAI Conference 2019 Conference Paper

Exploring Knowledge Graphs in an Interpretable Composite Approach for Text Entailment

Vivian S. Silva
André Freitas
Siegfried Handschuh

Recognizing textual entailment is a key task for many semantic applications, such as Question Answering, Text Summarization, and Information Extraction, among others. Entailment scenarios can range from a simple syntactic variation to more complex semantic relationships between pieces of text, but most approaches try a one-size-fits-all solution that usually favors some scenario to the detriment of another. We propose a composite approach for recognizing text entailment which analyzes the entailment pair to decide whether it must be resolved syntactically or semantically. We also make the answer interpretable: whenever an entailment is solved semantically, we explore a knowledge base composed of structured lexical definitions to generate natural language humanlike justifications, explaining the semantic relationship holding between the pieces of text. Besides outperforming wellestablished entailment algorithms, our composite approach gives an important step towards Explainable AI, using world knowledge to make the semantic reasoning process explicit and understandable.

PDF Details

AAAI Conference 2018 Conference Paper

Recognizing and Justifying Text Entailment Through Distributional Navigation on Definition Graphs

Vivian Silva
Siegfried Handschuh
André Freitas

Text entailment, the task of determining whether a piece of text logically follows from another piece of text, has become an important component for many natural language processing tasks, such as question answering and information retrieval. For entailments requiring world knowledge, most systems still work as a “black box”, providing a yes/no answer that doesn’t explain the reasoning behind it. We propose an interpretable text entailment approach that, given a structured deﬁnition graph, uses a navigation algorithm based on distributional semantic models to ﬁnd a path in the graph which links text and hypothesis. If such path is found, it is used to provide a human-readable justiﬁcation explaining why the entailment holds. Experiments show that the proposed approach present results comparable to some well-established entailment algorithms, while also meeting Explainable AI requirements, supplying clear explanations which allow the inference model interpretation.

PDF Details