32 citations · 85 across the 50 of their papers we have counts for
13 papers · 1 filter
SciR: A Controllable Benchmark for Scientific Reasoning in LLMs
Pierre Beckmann, Marco Valentino, Andre Freitas
Three paradigmatic forms of inference recur across scientific reasoning: deduction, induction, and causal abduction. Reliably evaluating LLMs on these in scientific settings is cur…
Neurosymbolic Clinical Trial Matching via LLM-Driven Abduction and Logical Verification
Baiyang Qu, Leonardo Ranaldi, Xi Wang +1
Large Language Models (LLMs) offer a promising path to automate Clinical Trial Matching (CTM), but still struggle with the deterministic verification required for complex eligibili…
Compartmentalised Agentic Reasoning for Clinical NLI
Maël Jullien, Lei Xu, Marco Valentino +1
Large language models can produce fluent judgments for clinical natural language inference, yet they frequently fail when the decision requires the correct inferential schema rathe…
The Knowledge-Reasoning Dissociation: Fundamental Limitations of LLMs in Clinical Natural Language Inference
Maël Jullien, Marco Valentino, André Freitas
Large language models are often assumed to acquire increasingly structured, generalizable internal representations simply by scaling data and parameters. We interrogate this assump…
Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
Marco Valentino, Geonhee Kim, Dhairya Dalal +2
Large language models (LLMs) exhibit reasoning biases, often conflating content plausibility with formal logical validity. This can lead to wrong inferences in critical domains, wh…
PEIRCE: Unifying Material and Formal Reasoning via LLM-Driven Neuro-Symbolic Refinement
Xin Quan, Marco Valentino, Danilo S. Carvalho +2
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…
Integrating Expert Knowledge into Logical Programs via LLMs
Franciszek Górski, Oskar Wysocki, Marco Valentino +1
This paper introduces ExKLoP, a novel framework designed to evaluate how effectively Large Language Models (LLMs) integrate expert knowledge into logical reasoning systems. This ca…
Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers
Mokanarangan Thayaparan, Marco Valentino, André Freitas
Integer Linear Programming (ILP) provides a viable mechanism to encode explicit and controllable assumptions about explainable multi-hop inference with natural language. However, a…
Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AI
Marco Valentino, André Freitas
A fundamental research goal for Explainable AI (XAI) is to build models that are capable of reasoning through the generation of natural language explanations. However, the methodol…
ExplanationLP: Abductive Reasoning for Explainable Science Question Answering
Mokanarangan Thayaparan, Marco Valentino, André Freitas
We propose a novel approach for answering and explaining multiple-choice science questions by reasoning on grounding and abstract inference chains. This paper frames question answe…
Case-Based Abductive Natural Language Inference
Marco Valentino, Mokanarangan Thayaparan, André Freitas
Most of the contemporary approaches for multi-hop Natural Language Inference (NLI) construct explanations considering each test case in isolation. However, this paradigm is known t…
Unification-based Reconstruction of Multi-hop Explanations for Science Questions
Marco Valentino, Mokanarangan Thayaparan, André Freitas
This paper presents a novel framework for reconstructing multi-hop explanations in science Question Answering (QA). While existing approaches for multi-hop reasoning build explanat…
Identifying Supporting Facts for Multi-hop Question Answering with Document Graph Networks
Mokanarangan Thayaparan, Marco Valentino, Viktor Schlegel +1
Recent advances in reading comprehension have resulted in models that surpass human performance when the answer is contained in a single, continuous passage of text. However, compl…