arXiv AI By Xuyao Feng, Antonis Bikakis

Pairwise Logical Selection of Enthymeme Completions under Semantic-Link Uncertainty

Read the original on arXiv AI →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jul 17

HABIB_TAZ at SemEval-2026 Task 11: Disentangling Formal Logic from Content via Synthetic Training and Multi-Objective Optimization

arXiv:2607. 14349v1 Announce Type: cross Abstract: While Large Language Models (LLMs) excel in many general NLP tasks, their formal reasoning capabilities are often compromised by content effects, demonstrating a measurable bias towards real-world plausibility.

By Abdullah Shaikh, Zain Naqi, Taha Zahid, Sandesh Kumar, Abdul Samad
arXiv AI
Jul 20

RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization

arXiv:2605. 04539v4 Announce Type: replace-cross Abstract: Direct Preference Optimization (DPO), the efficient alternative to PPO-based RLHF, falls short on knowledge-intensive generation: standard preference signals from human annotators or LLM judges exhibit a systematic verbosity bias that rewards fluency over logical correctness.

By Qiming Bao, Juho Leinonen, Paul Denny, Michael J. Witbrock
arXiv AI
Jul 15

Rethinking Reward Models for Multi-Domain Test-Time Scaling

arXiv:2510. 00492v3 Announce Type: replace Abstract: The reliability of large language models (LLMs) during test-time scaling is often assessed with \emph{external verifiers} or \emph{reward models} that distinguish correct reasoning from flawed logic.

By Dong Bok Lee, Seanie Lee, Sangwoo Park, Minki Kang, Jinheon Baek, Dongki Kim, Dominik Wagner, Jiongdao Jin, Heejun Lee, Tobias Bocklet, Jinyu Wang, Jingjing Fu, Sung Ju Hwang, Jiang Bian, Lei Song