Danilo S. Carvalho

Yingji Zhang, Marco Valentino, Danilo S. Carvalho et al.

The injection of syntactic information in Variational AutoEncoders (VAEs) has been shown to result in an overall improvement of performances and generalisation. An effective strategy to achieve such a goal is to separate the encoding of distributional semantic features and syntactic structures into heterogeneous latent spaces via multi-task learning or dual encoder architectures. However, existing works employing such techniques are limited to LSTM-based VAEs. In this paper, we investigate latent space separation methods for structural syntactic injection in Transformer-based VAE architectures (i.e., Optimus). Specifically, we explore how syntactic structures can be leveraged in the encoding stage through the integration of graph-based and sequential models, and how multiple, specialised latent representations can be injected into the decoder's attention mechanism via low-rank operators. Our empirical evaluation, carried out on natural language sentences and mathematical expressions, reveals that the proposed end-to-end VAE architecture can result in a better overall organisation of the latent space, alleviating the information loss occurring in standard VAE setups, resulting in enhanced performances on language modelling and downstream generation tasks.

Yingji Zhang, Danilo S. Carvalho, André Freitas

Formal/symbolic semantics can provide canonical, rigid controllability and interpretability to sentence representations due to their \textit{localisation} or \textit{composition} property. How can we deliver such property to the current distributional sentence representations to control and interpret the generation of language models (LMs)? In this work, we theoretically frame the sentence semantics as the composition of \textit{semantic role - word content} features and propose the formal semantic geometry. To inject such geometry into Transformer-based LMs (i.e. GPT2), we deploy Transformer-based Variational AutoEncoder with a supervision approach, where the sentence generation can be manipulated and explained over low-dimensional latent Gaussian space. In addition, we propose a new probing algorithm to guide the movement of sentence vectors over such geometry. Experimental results reveal that the formal semantic geometry can potentially deliver better control and interpretation to sentence generation.

Danilo S. Carvalho, Giangiacomo Mercatali, Yingji Zhang et al.

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised or rely on synthetic datasets with known generative factors. We argue that recurrent syntactic and semantic regularities in textual data can be used to provide the models with both structural biases and generative factors. We leverage the semantic structures present in a representative and semantically dense category of sentence types, definitional sentences, for training a Variational Autoencoder to learn disentangled representations. Our experimental results show that the proposed model outperforms unsupervised baselines on several qualitative and quantitative benchmarks for disentanglement, and it also improves the results in the downstream task of definition modeling.

Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann et al.

Explainable natural language inference aims to provide a mechanism to produce explanatory (abductive) inference chains which ground claims to their supporting premises. A recent corpus called EntailmentBank strives to advance this task by explaining the answer to a question using an entailment tree \cite{dalvi2021explaining}. They employ the T5 model to directly generate the tree, which can explain how the answer is inferred. However, it lacks the ability to explain and control the generation of intermediate steps, which is crucial for the multi-hop inference process. % One recent corpus, EntailmentBank, aims to push this task forward by explaining an answer to a question according to an entailment tree \cite{dalvi2021explaining}. They employ T5 to generate the tree directly, which can explain how the answer is inferred but cannot explain how the intermediate is generated, which is essential to the multi-hop inference process. In this work, we focus on proposing a controlled natural language inference architecture for multi-premise explanatory inference. To improve control and enable explanatory analysis over the generation, we define lexical inference types based on Abstract Meaning Representation (AMR) graph and modify the architecture of T5 to learn a latent sentence representation (T5 bottleneck) conditioned on said type information. We also deliver a dataset of approximately 5000 annotated explanatory inference steps, with well-grounded lexical-symbolic operations. Experimental results indicate that the inference typing induced at the T5 bottleneck can help T5 to generate a conclusion under explicit control.

Nura Aljaafari, Danilo S. Carvalho, Andre Freitas

Mechanistic interpretability produces circuit-level causal analyses of neural network behaviour, but discovered circuits often remain isolated experimental artefacts: there is no shared formal representation for what circuits compute, how they relate, or when two findings provide evidence for the same mechanism. This work provides a formal infrastructure for cumulative mechanistic science by treating circuit interpretation as inductive theory construction. Each circuit is characterised at two levels: a Causal Functional Signature (CFS), which grounds component behaviour in causal attribution evidence and token role profiles, and an architectural signature $τ_{\mathrm{arch}}$, learned by inductive logic programming (ILP) from scale-invariant structural predicates. Together, these constitute a formal coherence layer that makes mechanistic claims explicit, comparable via $θ$-subsumption, and portable across model scales. CFS reveals qualitatively distinct computational strategies across task types, including attention-mediated copying versus MLP-mediated binding. ILP signatures achieve substantially better structural separation than graph kernel and feature-vector baselines, and support principled transfer across model scales and architecture families.

Danilo S. Carvalho, Edoardo Manino, Julia Rozanova et al.

This work proposes a novel methodology for measuring compositional behavior in contemporary language embedding models. Specifically, we focus on adjectival modifier phenomena in adjective-noun phrases. In recent years, distributional language representation models have demonstrated great practical success. At the same time, the need for interpretability has elicited questions on their intrinsic properties and capabilities. Crucially, distributional models are often inconsistent when dealing with compositional phenomena in natural language, which has significant implications for their safety and fairness. Despite this, most current research on compositionality is directed towards improving their performance on similarity tasks only. This work takes a different approach, introducing three novel tests of compositional behavior inspired by Montague semantics. Our experimental results indicate that current neural language models do not behave according to the expected linguistic theories. This indicates that current language models may lack the capability to capture the semantic properties we evaluated on limited context, or that linguistic theories from Montagovian tradition may not match the expected capabilities of distributional models.

Mauricio Jacobo-Romero, Danilo S. Carvalho, Andre Freitas

In this work, we examined Business Process (BP) production as a signal; this novel approach explores a BP workflow as a linear time-invariant (LTI) system. We analysed BP productivity in the frequency domain; this standpoint examines how labour and capital act as BP input signals and how their fundamental frequencies affect BP production. Our research also proposes a simulation framework of a BP in the frequency domain for estimating productivity gains due to the introduction of automation steps. Our ultimate goal was to supply evidence to address Solow's Paradox.

Mauricio Jacobo-Romero, Danilo S. Carvalho, André Freitas

This paper proposes a novel productivity estimation model to evaluate the effects of adopting Artificial Intelligence (AI) components in a production chain. Our model provides evidence to address the "AI's" Solow's Paradox. We provide (i) theoretical and empirical evidence to explain Solow's dichotomy; (ii) a data-driven model to estimate and asses productivity variations; (iii) a methodology underpinned on process mining datasets to determine the business process, BP, and productivity; (iv) a set of computer simulation parameters; (v) and empirical analysis on labour-distribution. These provide data on why we consider AI Solow's paradox a consequence of metric mismeasurement.

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Locating and editing knowledge in large language models (LLMs) is crucial for enhancing their accuracy, safety, and inference rationale. We introduce ``concept editing'', an innovative variation of knowledge editing that uncovers conceptualisation mechanisms within these models. Using the reverse dictionary task, inference tracing, and input abstraction, we analyse the Multi-Layer Perceptron (MLP), Multi-Head Attention (MHA), and hidden state components of transformer models. Our results reveal distinct patterns: MLP layers employ key-value retrieval mechanism and context-dependent processing, which are highly associated with relative input tokens. MHA layers demonstrate a distributed nature with significant higher-level activations, suggesting sophisticated semantic integration. Hidden states emphasise the importance of the last token and top layers in the inference process. We observe evidence of gradual information building and distributed representation. These observations elucidate how transformer models process semantic information, paving the way for targeted interventions and improved interpretability techniques. Our work highlights the complex, layered nature of semantic processing in LLMs and the challenges of isolating and modifying specific concepts within these models.

Philip Osborne, Danilo S. Carvalho, André Freitas

We present elsciRL, an open-source Python library to facilitate the application of language solutions on reinforcement learning problems. We demonstrate the potential of our software by extending the Language Adapter with Self-Completing Instruction framework defined in (Osborne, 2024) with the use of LLMs. Our approach can be re-applied to new applications with minimal setup requirements. We provide a novel GUI that allows a user to provide text input for an LLM to generate instructions which it can then self-complete. Empirical results indicate that these instructions \textit{can} improve a reinforcement learning agent's performance. Therefore, we present this work to accelerate the evaluation of language solutions on reward based environments to enable new opportunities for scientific discovery.

João Pedro Gandarela, Danilo S. 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.

Yingji Zhang, Danilo S. Carvalho, Marco Valentino et al.

Achieving precise semantic control over the latent spaces of Variational AutoEncoders (VAEs) holds significant value for downstream tasks in NLP as the underlying generative mechanisms could be better localised, explained and improved upon. Recent research, however, has struggled to achieve consistent results, primarily due to the inevitable loss of semantic information in the variational bottleneck and limited control over the decoding mechanism. To overcome these challenges, we investigate discrete latent spaces in Vector Quantized Variational AutoEncoders (VQVAEs) to improve semantic control and generation in Transformer-based VAEs. In particular, We propose T5VQVAE, a novel model that leverages the controllability of VQVAEs to guide the self-attention mechanism in T5 at the token-level, exploiting its full generalization capabilities. Experimental results indicate that T5VQVAE outperforms existing state-of-the-art VAE models, including Optimus, in terms of controllability and preservation of semantic information across different tasks such as auto-encoding of sentences and mathematical expressions, text transfer, and inference. Moreover, T5VQVAE exhibits improved inference capabilities, suggesting potential applications for downstream natural language and symbolic reasoning tasks.

Xin Quan, Marco Valentino, Danilo S. Carvalho et al.

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the latter focusing on their logical and structural validity. Large Language Models (LLMs), by virtue of their extensive pre-training on large textual corpora, exhibit strong capabilities in material inference. However, their reasoning often lacks formal rigour and verifiability. At the same time, LLMs' linguistic competence positions them as a promising bridge between natural and formal languages, opening up new opportunities for combining these two modes of reasoning. In this paper, we introduce PEIRCE, a neuro-symbolic framework designed to unify material and formal inference through an iterative conjecture-criticism process. Within this framework, LLMs play the central role of generating candidate solutions in natural and formal languages, which are then evaluated and refined via interaction with external critique models. These critiques include symbolic provers, which assess formal validity, as well as soft evaluators that measure the quality of the generated arguments along linguistic and epistemic dimensions such as plausibility, coherence, and parsimony. While PEIRCE is a general-purpose framework, we demonstrate its capabilities in the domain of natural language explanation generation - a setting that inherently demands both material adequacy and formal correctness.

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Understanding the internal mechanisms of large language models (LLMs) is integral to enhancing their reliability, interpretability, and inference processes. We present Constituent-Aware Pooling (CAP), a methodology designed to analyse how LLMs process compositional linguistic structures. Grounded in principles of compositionality, mechanistic interpretability, and information theory, CAP systematically intervenes in model activations through constituent-based pooling at various model levels. Our experiments on inverse definition modelling, hypernym and synonym prediction reveal critical insights into transformers' limitations in handling compositional abstractions. No specific layer integrates tokens into unified semantic representations based on their constituent parts. We observe fragmented information processing, which intensifies with model size, suggesting that larger models struggle more with these interventions and exhibit greater information dispersion. This fragmentation likely stems from transformers' training objectives and architectural design, preventing systematic and cohesive representations. Our findings highlight fundamental limitations in current transformer architectures regarding compositional semantics processing and model interpretability, underscoring the critical need for novel approaches in LLM design to address these challenges.

Yingji Zhang, Danilo S. Carvalho, Ian Pratt-Hartmann et al.

Deep generative neural networks, such as Variational AutoEncoders (VAEs), offer an opportunity to better understand and control language models from the perspective of sentence-level latent spaces. To combine the controllability of VAE latent spaces with the state-of-the-art performance of recent large language models (LLMs), we present in this work LlaMaVAE, which combines expressive encoder and decoder models (sentenceT5 and LlaMA) with a VAE architecture, aiming to provide better text generation control to LLMs. In addition, to conditionally guide the VAE generation, we investigate a new approach based on flow-based invertible neural networks (INNs) named Invertible CVAE. Experimental results reveal that LlaMaVAE can outperform the previous state-of-the-art VAE language model, Optimus, across various tasks, including language modelling, semantic textual similarity and definition modelling. Qualitative analysis on interpolation and traversal experiments also indicates an increased degree of semantic clustering and geometric consistency, which enables better generation control.

Danilo S. Carvalho, Yingji Zhang, Harriet Unsworth et al.

We present LangVAE, a novel framework for modular construction of variational autoencoders (VAEs) on top of pre-trained large language models (LLMs). Such language model VAEs can encode the knowledge of their pre-trained components into more compact and semantically disentangled representations. The representations obtained in this way can be analysed with the LangVAE companion framework: LangSpace, which implements a collection of probing methods, such as vector traversal and interpolation, disentanglement measures, and cluster visualisations. LangVAE and LangSpace offer a flexible, efficient and scalable way of building and analysing textual representations, with simple integration for models available on the HuggingFace Hub. Additionally, we conducted a set of experiments with different encoder and decoder combinations, as well as annotated inputs, revealing a wide range of interactions across architectural families and sizes w.r.t. generalisation and disentanglement. Our findings demonstrate a promising framework for systematising the experimentation and understanding of textual representations.

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Large language models (LLMs) struggle with compositional generalisation, limiting their ability to systematically combine learned components to interpret novel inputs. While architectural modifications, fine-tuning, and data augmentation improve compositionality, they often have limited adaptability, face scalability constraints, or yield diminishing returns on real data. To address this, we propose CARMA, an intervention that enhances the stability and robustness of compositional reasoning in LLMs while preserving fine-tuned performance. CARMA employs mutual information regularisation and layer-wise stability constraints to mitigate feature fragmentation, ensuring structured representations persist across and within layers. We evaluate CARMA on inverse dictionary modelling and sentiment classification, measuring its impact on semantic consistency, performance stability, and robustness to lexical perturbations. Results show that CARMA reduces the variability introduced by fine-tuning, stabilises token representations, and improves compositional reasoning. While its effectiveness varies across architectures, CARMA's key strength lies in reinforcing learned structures rather than introducing new capabilities, making it a scalable auxiliary method. These findings suggest that integrating CARMA with fine-tuning can improve compositional generalisation while maintaining task-specific performance in LLMs.

Yingji Zhang, Marco Valentino, Danilo S. Carvalho et al.

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.

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Despite displaying semantic competence, large language models' internal mechanisms that ground abstract semantic structure remain insufficiently characterised. We propose a method integrating role-cross minimal pairs, temporal emergence analysis, and cross-model comparison to study how LLMs implement semantic roles. Our analysis uncovers: (i) highly concentrated circuits (89-94% attribution within 28 nodes); (ii) gradual structural refinement rather than phase transitions, with larger models sometimes bypassing localised circuits; and (iii) moderate cross-scale conservation (24-59% component overlap) alongside high spectral similarity. These findings suggest that LLMs form compact, causally isolated mechanisms for abstract semantic structure, and these mechanisms exhibit partial transfer across scales and architectures.

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Understanding when and how linguistic knowledge emerges during language model training remains a central challenge for interpretability. Most existing tools are post hoc, rely on scalar metrics, or require nontrivial integration effort, making comprehensive interpretability analysis difficult to deploy and maintain. We introduce TRACE, a modular toolkit for training and inference-time interpretability analysis of transformer models. It enables lightweight, in-training analysis of linguistic and representational signals, including features probing, intrinsic dimensionality, Hessian curvature, and output diagnostics. It integrates with ABSynth, a controllable synthetic corpus generator that provides structured annotations for precise evaluation of linguistic feature acquisition. Experiments with autoregressive transformers demonstrate that TRACE reveals developmental phenomena such as early syntactic emergence, delayed semantic acquisition, and representational compression, signals overlooked by traditional scalar metrics such as loss or accuracy. With minimal integration effort, the tool enables layer-wise diagnostics, convergence-based early stopping, and detection of structural errors, making transformer analysis interpretable, actionable, and reproducible.

Yingji Zhang, Danilo S. Carvalho, André Freitas

Integrating compositional and symbolic properties into current distributional semantic spaces can enhance the interpretability, controllability, compositionality, and generalisation capabilities of Transformer-based auto-regressive language models (LMs). In this survey, we offer a novel perspective on latent space geometry through the lens of compositional semantics, a direction we refer to as \textit{semantic representation learning}. This direction enables a bridge between symbolic and distributional semantics, helping to mitigate the gap between them. We review and compare three mainstream autoencoder architectures-Variational AutoEncoder (VAE), Vector Quantised VAE (VQVAE), and Sparse AutoEncoder (SAE)-and examine the distinctive latent geometries they induce in relation to semantic structure and interpretability.

Nura Aljaafari, Danilo S. Carvalho, André Freitas

Modern transformer models exhibit phase transitions during training, distinct shifts from memorisation to abstraction, but the mechanisms underlying these transitions remain poorly understood. Prior work has often focused on endpoint representations or isolated signals like curvature or mutual information, typically in symbolic or arithmetic domains, overlooking the emergence of linguistic structure. We introduce TRACE (Tracking Representation Abstraction and Compositional Emergence), a diagnostic framework combining geometric, informational, and linguistic signals to detect phase transitions in Transformer-based LMs. TRACE leverages a frame-semantic data generation method, ABSynth, that produces annotated synthetic corpora with controllable complexity, lexical distributions, and structural entropy, while being fully annotated with linguistic categories, enabling precise analysis of abstraction emergence. Experiments reveal that (i) phase transitions align with clear intersections between curvature collapse and dimension stabilisation; (ii) these geometric shifts coincide with emerging syntactic and semantic accuracy; (iii) abstraction patterns persist across architectural variants, with components like feedforward networks affecting optimisation stability rather than fundamentally altering trajectories. This work advances our understanding of how linguistic abstractions emerge in LMs, offering insights into model interpretability, training efficiency, and compositional generalisation that could inform more principled approaches to LM development.

Marco Valentino, Danilo S. Carvalho, André Freitas

Natural language definitions possess a recursive, self-explanatory semantic structure that can support representation learning methods able to preserve explicit conceptual relations and constraints in the latent space. This paper presents a multi-relational model that explicitly leverages such a structure to derive word embeddings from definitions. By automatically extracting the relations linking defined and defining terms from dictionaries, we demonstrate how the problem of learning word embeddings can be formalised via a translational framework in Hyperbolic space and used as a proxy to capture the global semantic structure of definitions. An extensive empirical analysis demonstrates that the framework can help imposing the desired structural constraints while preserving the semantic mapping required for controllable and interpretable traversal. Moreover, the experiments reveal the superiority of the Hyperbolic word embeddings over the Euclidean counterparts and demonstrate that the multi-relational approach can obtain competitive results when compared to state-of-the-art neural models, with the advantage of being intrinsically more efficient and interpretable.

Yingji Zhang, Danilo S. Carvalho, André Freitas

Disentangled latent spaces usually have better semantic separability and geometrical properties, which leads to better interpretability and more controllable data generation. While this has been well investigated in Computer Vision, in tasks such as image disentanglement, in the NLP domain sentence disentanglement is still comparatively under-investigated. Most previous work have concentrated on disentangling task-specific generative factors, such as sentiment, within the context of style transfer. In this work, we focus on a more general form of sentence disentanglement, targeting the localised modification and control of more general sentence semantic features. To achieve this, we contribute to a novel notion of sentence semantic disentanglement and introduce a flow-based invertible neural network (INN) mechanism integrated with a transformer-based language Autoencoder (AE) in order to deliver latent spaces with better separability properties. Experimental results demonstrate that the model can conform the distributed latent space into a better semantically disentangled sentence space, leading to improved language interpretability and controlled generation when compared to the recent state-of-the-art language VAE models.

Danilo S. Carvalho, Duc-Vu Tran, Van-Khanh Tran et al.

Legal professionals worldwide are currently trying to get up-to-pace with the explosive growth in legal document availability through digital means. This drives a need for high efficiency Legal Information Retrieval (IR) and Question Answering (QA) methods. The IR task in particular has a set of unique challenges that invite the use of semantic motivated NLP techniques. In this work, a two-stage method for Legal Information Retrieval is proposed, combining lexical statistics and distributional sentence representations in the context of Competition on Legal Information Extraction/Entailment (COLIEE). The combination is done with the use of disambiguation rules, applied over the rankings obtained through n-gram statistics. After the ranking is done, its results are evaluated for ambiguity, and disambiguation is done if a result is decided to be unreliable for a given query. Competition and experimental results indicate small gains in overall retrieval performance using the proposed approach. Additionally, an analysis of error and improvement cases is presented for a better understanding of the contributions.

Danilo S. Carvalho, Minh-Tien Nguyen, Tran Xuan Chien et al.

In the context of the Competition on Legal Information Extraction/Entailment (COLIEE), we propose a method comprising the necessary steps for finding relevant documents to a legal question and deciding on textual entailment evidence to provide a correct answer. The proposed method is based on the combination of several lexical and morphological characteristics, to build a language model and a set of features for Machine Learning algorithms. We provide a detailed study on the proposed method performance and failure cases, indicating that it is competitive with state-of-the-art approaches on Legal Information Retrieval and Question Answering, while not needing extensive training data nor depending on expert produced knowledge. The proposed method achieved significant results in the competition, indicating a substantial level of adequacy for the tasks addressed.