The paper presents a neuro‑symbolic approach for selecting the correct omitted component in enthymemes, extending prior work from missing‑premise to missing‑claim selection. It replaces binary entailment with logical‑resistance scores and introduces the Possible‑World Atom‑Link Formalization (PWAL), which marginalizes over alternative semantic‑link configurations while keeping translated formulae fixed. Experiments on five tasks show that PWAL improves strict accuracy by up to 30.86 percentage points and reduces tie rates significantly, while also providing a transparent trace of each comparison.
By Xuyao Feng, Antonis Bikakis
arXiv:2607. 19845v1 Announce Type: cross Abstract: This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences.
By Ahmad Pouramini, Mahsa Afsharizadeh
arXiv:2405.01259v2 Announce Type: replace
Abstract: Argumentation is an important cognitive activity that involves the scrutiny of arguments and counterarguments. When given an argument, it is desira...
By Xuyao Feng, Anthony Hunter
arXiv:2606. 02837v1 Announce Type: cross Abstract: Accurate translation from Natural Language to First-Order Logic (NL-to-FOL) underpins neurosymbolic AI systems and Natural Language Inference (NLI), making the quality of NL-to-FOL benchmarks essential -- yet these datasets have never been rigorously audited.
By Andrea Brunello, Cristian Curaba, Luca Geatti, Michele Mignani, Angelo Montanari, Nicola Saccomanno
The paper investigates whether natural language inference (NLI) can be performed using only interpretable, graph-based representations of evidence. It introduces a pipeline that decomposes sentences into atomic propositions, maps them to ConceptNet triples, and feeds three graphs—premise, hypothesis, and a retrieved ConceptNet subgraph—into a fine‑tuned 0.8‑billion‑parameter language model. On the SNLI dataset the graph‑only model reaches 89.7% accuracy, close to a text‑based baseline, while on ANLI it matches RoBERTa‑large on rounds R2 and R3 but lags on R1, illustrating a trade‑off between interpretability and performance.
By Younes Boufouss (LISN), Luc Pommeret (LISN, CNRS), Thomas Gerald (LISN), Patrick Paroubek (LISN, CNRS), Sophie Rosset (LISN, CNRS)
arXiv:2609.26610v1 Announce Type: new
Abstract: Despite their outstanding performance on many NLP tasks, LLMs face serious challenges related to semantic abstraction. In this study, we are interested...
By David Torres-Moreno, Jorge Hermosillo-Valadez
arXiv:2603. 06114v2 Announce Type: replace-cross Abstract: Real-world arguments in text and dialogues are normally enthymemes (i.
By Xuyao Feng, Anthony Hunter
This paper introduces Sentence Splitter, a self-supervised framework built upon a T5-based encoder--decoder architecture for uncovering the latent factual structure of natural language sentences. The proposed method identifies the semantic boundary between a descriptive prefix (head) and its factual completion (tail) by formulating sentence splitting as a discrete segmentation problem, where a sentence of length $N$ admits $N$ possible split points but only one recovers the intended head--tail structure.
CONSISTRE is a consistency‑aware framework for document‑level relation extraction that tackles contradictions in large language model predictions. It offers two tracks: an inference‑time track that refines black‑box LLM outputs through constraint‑aware prompting, verification, and self‑reflection, and a training‑time track that distills consistency knowledge into smaller open‑source models via supervised fine‑tuning and reinforcement learning. Experiments on DocRED show both tracks outperform baselines, with the inference‑time track matching competitive F1 scores and the training‑time track narrowing the performance gap to proprietary LLMs while reducing inference cost.
By Mingxuan Sun
Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure.
arXiv:2505.22635v2 Announce Type: replace-cross
Abstract: A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoni...
By Fangcong Yin, Zeyu Leo Liu, Liu Leqi, Xi Ye, Greg Durrett
arXiv:2608.30627v1 Announce Type: new
Abstract: As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token pred...
By Haoran Que, Jiajun Shi, Ting Huang, Renming Pang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Shen Yan, Wei Ye, Shikun Zhang