Searcharxiv⌕ Search

arXiv subjects

André Freitas

Publications and source records attributed to André Freitas.

At least 19 recordsLinked to original sources
arXiv2026

MechReasoner: A Simulator and Benchmark for Mechanistic Reasoning in Qualitative Physics

This work introduces MechReasoner, a mechanistic qualitative simulator grounded in confluence-based qualitative physics, together with a benchmark for mechanistic inference. Current large language models (LLMs) generate fluent mechanistic descriptions that do not reliably follow from underlying structural and causal constraints. The benchmark tests whether answers preserve simulator-licensed ambiguity, quantified claims, episode-graph transition evidence, repairs, and trace-support judgments. Its 1,120 items are generated deterministically from admissible interpretation sets, component states, scenario restrictions, confluence constraints, and derivation steps across 18 catalog mechanisms and six task families. Each mechanism undergoes converter checks of structure and topology and behavioral checks against quantitative simulations. GPT-5.5 accuracy decreases as family-specific mechanistic complexity increases, from 76.1% in the lowest-complexity bucket (B1) to 38.0% in the highest-complexity bucket (B4). The negative association remains after controls for rendered-prompt and expected-answer length. These results show that qualitative simulators can support auditable NLP benchmarks for mechanistic inference.

cs.AI↗
arXiv2026

Effective Graph and Rank-based Contextual Embeddings for Textual and Multimedia Data

In a data-driven world, efficiently organizing and mapping relationships between objects is crucial. Graphs are powerful tools for modeling these connections, being widely used in social networks, telecommunications, and biology. However, graph-based methods often face high computational costs, particularly in memory and space usage. To address this, graph embedding techniques, also referred to as Network Representation Learning, encode graph information into lower-dimensional representations while preserving structural aspects. Traditional methods, however, lack interpretable dimensions. RaDE (Rank Diffusion Embedding) introduces a new approach using rank-based information, with a key step being the selection of a representative subset of nodes to provide interpretability for its dimensions and improve retrieval tasks. Despite its potential, RaDE's original proposal did not fully explore the effectiveness of representative subset selection across different classes or evaluate embeddings in tasks like classification and clustering. Inspired by RaDE, this work introduces GRaCE (Graph and Rank-based Contextual Embeddings), a fully unsupervised framework that generates interpretable embeddings by leveraging robust rank-based measures for representative subset selection and node embedding. GRaCE surpasses RaDE and Original Features across diverse datasets, including textual and image collections, excelling in retrieval, classification, and clustering tasks, considering state-of-the-art Transformer models as feature descriptors and Graph Convolutional Networks models in classification tasks.

cs.LG↗
arXiv2026

Autoformalizing Argumentative Material Inferences

Natural language arguments are compelling before they are formally explicit. A premise supports a claim through defeasible warrants, background commitments, and exception conditions that the text leaves implicit. However, formal verification requires the opposite. Making such arguments machine-checkable requires constructing the missing commitments, not only translating given sentences into logic. Construction, however, carries a risk that translation does not: a system free to add premises can make any claim provable, and a formally valid proof may assert the claim outright, prove it without the original premise, or establish more than the claim itself. We address this problem by formulating autoformalization for argumentative material inference as guard completion, in which non-monotonic material support is turned into monotonic formal inference relative to an explicitly constructed guard set. A completion is accepted only when its proof both passes the theorem prover and survives contrastive tests of premise dependence and claim selectivity. We implement this formulation in GUARD, a neuro-symbolic framework in which LLMs construct and formalize candidate guards, Isabelle/HOL verifies the resulting theories and returns step-level feedback for iterative refinement, and the system abstains when no faithful completion can be reached. Our empirical results on Debatepedia and ARCT using different LLMs demonstrate that GUARD yields significant improvements in verified-faithful (+35.3, +32.9 points) and substantial reductions in leakage (-25.9, -21.9 points) over the state-of-the-art LLM-driven theorem proving approach. Moreover, we show that the symbolic soft critique and the explicit assumption layer account for most of these gains, with the soft critique also improving the initial validity of the elicited context and reducing the number of iterations required for successful verification.

cs.CL↗
arXiv2026

Bridging Linguistic Structure and Mechanistic Interpretability for Conceptual Interpretation in Language Models

Understanding how language models compose meaning from linguistic input remains a central problem in interpretability research. Mechanistic studies have attributed functional roles to core transformer components; however, these findings derive largely from factual retrieval settings. Whether the same mechanisms support \textit{conceptual interpretation}, the compositional mapping from definitional expressions to abstract meaning, remains insufficiently characterised. We introduce \textit{DSRA} (Definitional Semantic Role Analysis), a methodology that applies causal tracing within the reverse dictionary task and augments restoration traces with definitional semantic roles (DSRs) grounded in Argument Structure Theory. This linguistic overlay identifies which compositional functions (e.g., genus, differentia quality) are associated with high-recovery states, extending activation patching beyond token-level localisation. Applied to GPT-J-6B (English) and BERTIN GPT-J-6B (Spanish), the results show that MLP layers associate content-bearing tokens with high-specificity DSR categories in early layers, MHA layers distribute integration across middle-to-upper layers with concentration at the final token, and hidden states aggregate information in upper layers. Alignment between restored states and DSR categories indicates systematic correspondence between internal activations and definitional structure, with consistent localisation patterns across both languages.

cs.CL↗
arXiv2026

Learning turbulent transport via Mori--Zwanzig graph neural networks

We introduce a Mori--Zwanzig graph neural network (MZ--GNN) framework for learning reduced-order Lagrangian dynamics of tracer particles in homogeneous isotropic turbulence. The model represents particle acceleration as a finite-memory expansion over present and delayed particle-neighborhood graphs, with each memory contribution parameterized by an equivariant message-passing graph neural network. By construction, the architecture respects the relevant physical symmetries of the problem, including permutation equivariance, Galilean invariance, and equivariance under rotations and reflections. Trained on direct numerical simulation data, the model is rolled out autoregressively and evaluated on observables that are not imposed during training. We show that memory is essential for recovering the intermittent, heavy-tailed acceleration statistics, and that the learned dynamics accurately reproduce single-particle dispersion, pair-dispersion statistics, and four-particle tetrad geometry. Our results establish a physically structured, scalable route to data-driven multi-particle simulation of turbulent transport, and a template for learning reduced dynamics of correlated, symmetry-rich particle systems.

physics.flu-dyn↗
arXiv2026

Reasoning without Gold Standards: A Proxy-Judge Theory of Autoformalization

Complex reasoning tasks increasingly require systems to produce outputs whose correctness cannot be judged by exact match against a single reference. Autoformalization (AF) is a representative example; it asks a model to translate informal mathematical or logical reasoning into a formally checkable object, yet expert-validated formalizations do not scale beyond toy cases and a single informal argument can admit many valid formal renderings. Progress therefore depends on whether partial, structured proxies can substitute for exact references. We introduce a reference-free proxy-judge framework for AF that replaces gold-standard matching with a vector of per-axis property checks. The framework organizes the proxy along three structural scopes that cover global properties of the elicited object, per-module properties internal to its sub-components, and cross-domain properties that re-align it to the informal source, and aggregates each axis into a verdict vector. The vector drives a reflective refinement loop in which a violated coordinate routes the controller to a matching repair target, so each iteration changes only what is judged wrong. Under bounded judge noise, the expected intrinsic gap contracts geometrically to a noise-dependent plateau. Across seven formalization backbones on miniF2F, ProofNet, e-SNLI, and ProntoQA, refinement consistently lifts Pass Rate over the single-shot ICL baseline, and the per-axis proxy outperforms a matched scalar proxy on benchmarks where the baseline has room to improve. Structured proxy judgments therefore provide both a practical refinement signal and a theoretical handle on convergence when exact references are unavailable.

cs.CL↗
arXiv2026

AbstRAG: Learning to Abstract for Retrieval Problems

Retrieval-augmented generation often fails when the query, the document evidence, and the user's intent are expressed at different levels of abstraction. A query may ask about a class, a relation, or an event, while the document only states specific instances, indirect framings, or scoped formulations. We define this mismatch as an abstraction gap: the minimal set of typed assumptions required to align query intent with the available evidence. To close this gap, we introduce AbstRAG, which treats abstraction as an explicit retrieval object. AbstRAG decomposes the query--evidence gap into expression, conceptual, intent--evidence, and event-type components, and scores relevance by combining match quality, a query-independent utility prior, and the cost of the required bridges. Its central mechanism is reflective refinement: a critic diagnoses retrieval failures, localizes the failed abstraction operator, proposes a minimal stage-specific patch, and accepts the patch only under sufficiency and compression controls. Across three within-document retrieval benchmarks against seven baselines, AbstRAG outperforms on nDCG@10 in 18 of 21 paired-bootstrap contrasts and improves generation accuracy by 1.9%, 5.2%, and 4.0% across the three benchmarks; ablations confirm that reflective refinement drives most of the retrieval gain and the compression control alone reduces over-expansion false positives from 73.7% to 0% on a stress slice.

cs.CL↗
arXiv2026

R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search

Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, where a system must plan, use tools, and act over extended horizons, fluency does not ensure reliable delivery. We trace this gap to three coupled structural failures: errors propagate without localization, worst-case perturbations go unevaluated, and accumulated knowledge is never invalidated. We argue these share a root cause: abductive, counterfactual, meta-inductive, corrective, and inductive reasoning pull a shared context in incompatible directions. We introduce Reflective Adversarial Pareto Search (R-APS), to our knowledge the first method addressing all three failures jointly via reasoning-mode decomposition, allocating each reasoning mode its own context and orchestrating interaction across three timescales: staged compositional reasoning with a typed validation critic (failure localization), sensitivity-guided counterfactual stress-testing as a first-class Pareto objective (robustness), and meta-inductive rule extraction with explicit invalidation (persistent memory). R-APS requires no fine-tuning and operates on a frozen LLM purely via structured protocol design. We evaluate on planar mechanism synthesis (robotics, prosthetics, mechanical design), with every candidate checked by a kinematic solver. On 32 target trajectories, R-APS delivers robustness certificates 3.5x tighter than uniform-perturbation baselines, 46% faster iterations-to-first-admission, and 2.1x Chamfer-distance reduction over Enum+GA while jointly controlling bar-count and worst-case robustness. Small 4B reasoning-specialized models prove competitive with general-purpose 70B backbones inside the protocol, suggesting structured protocols can partially offset model scale.

cs.AI↗
arXiv2026

Beyond Topical Similarity: Contrastive Evidence Retrieval with Interpretable Attention Alignment in RAG

Ensuring factuality and interpretability in RAG remains an open and urgent problem. We introduce Contrastive Evidence Rationale Attention (CERA), the first retrieval framework to employ subjectivity-based hard negative selection and inject an evidential inductive bias into contrastive learning through an auxiliary attention alignment loss. CERA fine-tunes a dense retriever using two training objectives: triplet-based contrastive learning and interpretable attention alignment, which supervises CLS-to-token attention using a part-of-speech-weighted masking distribution over human-annotated factual rationales as evidence signals. Experiments on a large corpus of clinical trial reports demonstrate that the subjectivity-based hard negative selection substantially improves retrieval effectiveness compared to both Contriever and hard negative selection baselines. Furthermore, rationale alignment improves faithfulness while maintaining competitive retrieval performance, supporting the hypothesis that attention can serve as a more faithful explanation of model behavior when guided by human rationales. Moving beyond topical similarity, CERA enables the retriever to identify the specific tokens that constitute supporting evidence, promoting more interpretable evidence selection in RAG systems.

cs.CL↗
arXiv2026

Symbolic Intermediaries as a Linguistic-Numerical Interface for LLM-Driven Geometric Reasoning

Large Language Models (LLMs) display reasoning capabilities over linguistic and symbolic objects but have limited capabilities to directly interpret the continuous numerical outputs of physics simulators, e.g., distances, curvatures, and trajectories that resist discrete tokenisation. Across spatially grounded engineering reasoning tasks, from mechanism design to motion planning, this defines a fundamental gap, which limits the wider application of LLMs within broader geometrical domains, for exmaple interfacing with physics simulators. We propose symbolic intermediaries, compact analytical expressions discovered via symbolic regression, as a structured interface that translates a simulator's numerical traces into a symbolic form, which language models can interpret, compare, and critique while preserving the original geometric semantics. Around this interface we build an agentic coordination-and-refinement loop: a design agent maps natural-language specifications to executable simulation code, a critique agent reasons over the shared symbolic vocabulary, and a revision step turns this feedback into grounded refinement decisions, enabling inference-time generalization without parameter updates. On the MSynth benchmark for planar mechanism synthesis, all three evaluated LLM agents outperform a budget-matched genetic-algorithm baseline by 19-53% (up to 63% lower median error with feedback), and analysis of the critique entries across three model architectures shows that the interface shifts reasoning from generic structural commentary to grounded geometric verification. The principle of translating continuous simulation outputs into symbolic forms generalises to any domain where simulator behaviour must be interpreted linguistically.

cs.AI↗
arXiv2026

GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving

Mathematical reasoning is a hallmark of human intelligence, requiring logical deduction, symbolic manipulation, and abstract thinking. Recent multimodal large language models (MLLMs) have demonstrated strong performance on geometry problems through multi-step reasoning. To better emulate human problem-solving, intermediate steps can incorporate auxiliary visual constructions, such as additional lines or points, which improve geometric interpretation and educational clarity. In this work, we introduce the GeoMathCode, where programmatic representations serve as intermediate visual outputs. We further conduct an in-depth analysis of the underlying reasoning geometry. Experimental results show that reasoning and code generation steps can be disentangled in the latent space, while supervised fine-tuning (SFT) makes the reasoning manifold more structured and informative. Moreover, hierarchical syntactic code structures emerge as disentangled latent subspaces, and contain more mathematical symbolic information than visual representations.

cs.CL↗
arXiv2026

Is Inference Mediated by Distinct Semantic Structures in LLMs? A Mechanistic Interpretation

Predicting a label correctly does not necessarily require representing the operation that produces it. Transformer representations are known to carry label-level information, but whether they encode semantic operations producing those labels is unclear. We investigate this in Natural Language Inference using controlled premise-hypothesis pairs that differ by a single semantic transformation. Using layer-wise activations, we estimate operation-level subspaces via SVD and test their causal relevance through activation steering in four open-weight decoder models. Transformation effects are decodable with $84.8$-$99\%$ accuracy and occupy partially distinct but overlapping subspaces, exceeding random-subspace baselines. Steering experiments show that these directions causally influence predictions, though steerability varies across models; cross-operation steering further reveals structured interference and a dissociation between subspace selectivity and cross-operation independence. These findings indicate that the models encode not only that a hypothesis relates to a premise but also, in part, how it does so, implying that mechanistic analysis and control should operate at the level of semantic operations rather than predicted labels alone.

cs.CL↗
arXiv2026

Monotonic Reference-Free Refinement for Autoformalization

While statement autoformalization has advanced rapidly, full-theorem autoformalization remains largely unexplored. Existing iterative refinement methods in statement autoformalization typically improve isolated aspects of formalization, such as syntactic correctness, but struggle to jointly optimize multiple quality dimensions, which is critical for full-theorem autoformalization. We introduce a reference-free iterative monotonic process at inference time for full-theorem autoformalization that leverages complementary feedback from theorem provers and LLM-based judges, without access to ground-truth or existing formalizations and without human intervention. Our approach optimizes a masked composite objective over Formal Validity, Logical Preservation, Mathematical Consistency, and Formal Quality, guided by a responsiveness map that indicates how different LLMs acting as different roles preferentially improve each dimension. We further propose an acceptance policy that guarantees certified monotonic improvement, and provide conditions ensuring convergence and termination. Empirical experiments demonstrate the proposed process enables simultaneous improvement across multiple dimensions, achieving 100.00% formal validity and a 90.27% overall score on miniF2F, and 77.96% formal validity and a 52.45% overall score on ProofNet.

cs.CL↗
arXiv2026

Language Models Refine Mechanical Linkage Designs Through Symbolic Reflection and Modular Optimisation

Designing mechanical linkages involves combinatorial topology selection and continuous parameter fitting. We show that language models can systematically improve linkage designs through symbolic representations. Language model agents explore discrete topologies while numerical optimisers fit continuous parameters. A symbolic lifting operator translates simulator trajectories into qualitative descriptors, motion labels, temporal predicates, and structural diagnostics that models interpret across iterative design cycles. Across six engineering-relevant motion targets and three open-source models (Llama 3.3 70B, Qwen3 4B, Qwen3 MoE 30B-A3B), the modular architecture reduces geometric error by up to 68% and improves structural validity by up to 134% over monolithic baselines. Critically, 78.6% of iterative refinement trajectories show measurable improvement, with the system correctly diagnosing overconstraint (56.3%) and underconstraint (35.6%) failure modes and proposing grounded corrections. Models across all three families acquire interpretable mechanical reasoning strategies without fine-tuning, demonstrating that principled symbolic abstraction bridges generative AI and the numerical precision required for engineering design.

cs.AI↗
arXiv2026

Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder

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.

cs.CL↗
arXiv2026

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

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.

cs.AI↗
arXiv2026

A posteriori closure of turbulence models: are symmetries preserved?

Turbulence modeling remains a longstanding challenge in fluid dynamics. Recent advances in data-driven methods have led to a surge of novel approaches aimed at addressing this problem. This work builds upon our recent work [Phys. Rev. Fluids 10, 044602 (2025)], where we introduced a new closure for a shell model of turbulence using an a posteriori (or solver-in-the-loop) approach. Unlike most deep learning-based models, our method explicitly incorporates physical equations into the neural network framework, ensuring that the closure remains constrained by the underlying physics benefiting from enhanced stability and generalizability. In this paper, we further analyze the learned closure, probing its capabilities and limitations. In particular, we look at joint probability density functions between resolved and unresolved variables, as well as the scale invariance of multipliers (ratios between adjacent shells) within the inertial range. Although our model excels in reproducing high-order statistical moments, it breaks this known symmetry near the cutoff, indicating a fundamental limitation. We discuss the implications of these findings for subgrid-scale modeling in 3D turbulence and outline directions for future research.

physics.flu-dyn↗
arXiv2026

On the importance of stochasticity in closures of turbulence

Deterministic closures for coarse-grained turbulence models help reproduce mean statistics, but often fail to capture the finite-time growth of uncertainty. Using the framework of shell models as a quantitative multi-scale testbed, we compare fully resolved simulations with large-eddy simulations using either stochastic or deterministic subgrid closures. While in the fully resolved system a single microscopic perturbation is rapidly amplified by strongly chaotic dynamics, truncation produces a strong delay and suppression of variance growth when uncertainty is introduced through initial condition perturbations only. We show that a data-driven Langevin-type stochastic closure restores the correct timing and magnitude of variance growth across scales, demonstrating that sustained stochasticity is essential for predictability in reduced turbulent dynamics.

physics.flu-dyn↗