paper-with-me

Papers Formal Logic

“Formal Logic” 태그가 달린 논문 114편 · 필터 해제

Recover, Decode, Reguard: Guard-Agnostic Defense Amplification againstEncoded VLM Jailbreaks

2026-07-29 · Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Zijian Xiao 외 arxiv

Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet they judge an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a rare langu…

Formal Logic

Let AI Agents Translate Networks, Not Reason About Them

2026-07-24 · Hongyu Hè, Maria Apostolaki arxiv

A formal model enables verifying reachability, localizing an outage, or anticipating the blast radius of a change. Yet, virtually no production network has one, since writing a model by hand demands rare expertise and is…

Formal Logic

Invariant Discovery for Networked Systems

2026-07-24 · Hongyu Hè, Alexander Krentsel, Sylvia Ratnasamy, Maria Apostolaki arxiv

Invariants, the relations expected to hold among measured signals of a network, underpin applications from verification to traffic generation, telemetry imputation, and input validation, yet writing them by hand demands …

Formal Logic

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

2026-07-15 · Abdullah Shaikh, Zain Naqi, Taha Zahid, Sandesh Kumar 외 arxiv

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. In this p…

Logical ReasoningFormal Logic

ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling

2026-06-23 · Heng Ping, Arijit Bhattacharjee, Peiyu Zhang, Shixuan Li 외 arxiv

Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sustain gains as depth increases, exhibiting…

Formal Logic

Uncertainty Reasoning with Large Language Models for Explainable Disease Diagnosis

2026-05-25 · Xiaoyang Fan, Yufan Cai, Zhe Hou, Jin Song Dong arxiv

Clinical decision-making requires reasoning over incomplete, imprecise, and linguistically expressed patient narratives. While large language models (LLMs) excel at extracting latent information from natural language, th…

Medical DiagnosisFormal Logic

Toward Template-Free Explainability for Monte Carlo Tree Search

2026-05-15 · Siqi Lu, Mirsaleh Bahavarnia, Hiba Baroud, Yixuan Zhang 외 arxiv

Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorp…

Formal Logic

Neurosymbolic Auditing of Natural-Language Software Requirements

2026-05-13 · Bethel Hall, William Eiers arxiv

Natural-language software requirements are often ambiguous, inconsistent, and underspecified; in safety-critical domains, these defects propagate into formal models that verify the wrong specification and into implementa…

Formal Logic

Bridging Legal Interpretation and Formal Logic: Faithfulness, Assumption, and the Future of AI Legal Reasoning

2026-05-13 · Olivia Peiyu Wang, Leilani H. Gilpin arxiv

The growing adoption of large language models in legal practice brings both significant promise and serious risk. Legal professionals stand to benefit from AI that can reason over contracts, draft documents, and analyze …

Legal ReasoningFormal Logic

Abductive Reasoning with Probabilistic Commonsense

2026-05-08 · Joseph Cotnareanu, Chiara Roverato, Han Zhou, Didier Chetelat 외 arxiv

Recent efforts to improve the reasoning abilities of Large Language Models (LLMs) have focused on integrating formal logic solvers within neurosymbolic frameworks. A key challenge is that formal solvers lack commonsense …

Formal Logic

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis

2026-05-05 · Haoyu Zhang, Mohammad Zandsalimy, Shanu Sushmita arxiv

Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathematical problems --…

Formal Logic

Towards Lawful Autonomous Driving: Deriving Scenario-Aware Driving Requirements from Traffic Laws and Regulations

2026-04-27 · Bowen Jian, Rongjie Yu, Hong Wang, Liqiang Wang 외 arxiv

Driving in compliance with traffic laws and regulations is a basic requirement for human drivers, yet autonomous vehicles (AVs) can violate these requirements in diverse real-world scenarios. To encode law compliance int…

Autonomous VehiclesAutonomous DrivingFormal Logic

The Topological Dual of a Dataset: A Logic-to-Topology Encoding for AlphaGeometry-Style Data

2026-04-20 · Anthony Bordg arxiv

AlphaGeometry represents a milestone in neuro-symbolic reasoning, yet its architecture faces a log-linear scaling bottleneck within its symbolic deduction engine that limits its efficiency as problem complexity increases…

Formal Logic

FregeLogic at SemEval 2026 Task 11: A Hybrid Neuro-Symbolic Architecture for Content-Robust Syllogistic Validity Prediction

2026-04-20 · Adewale Akinfaderin, Nafi Diallo arxiv

We present FregeLogic, a hybrid neuro-symbolic system for SemEval-2026 Task 11 (Subtask 1), which addresses syllogistic validity prediction while reducing content effects on predictions. Our approach combines an ensemble…

Formal Logic

The Cognitive Penalty: Ablating System 1 and System 2 Reasoning in Edge-Native SLMs for Decentralized Consensus

2026-04-18 · Syed Muhammad Aqdas Rizvi arxiv

Decentralized Autonomous Organizations (DAOs) are inclined explore Small Language Models (SLMs) as edge-native constitutional firewalls to vet proposals and mitigate semantic social engineering. While scaling inference-t…

Adversarial RobustnessFormal Logic

Towards Effective In-context Cross-domain Knowledge Transfer via Domain-invariant-neurons-based Retrieval

2026-04-07 · Jianzhi Yan, Zhiming Li, Le Liu, Zike Yuan 외 arxiv

Large language models (LLMs) have made notable progress in logical reasoning, yet still fall short of human-level performance. Current boosting strategies rely on expert-crafted in-domain demonstrations, limiting their a…

Mathematical ReasoningLogical ReasoningFormal Logic

Position: Logical Soundness is not a Reliable Criterion for Neurosymbolic Fact-Checking with LLMs

2026-04-05 · Jason Chan, Robert Gaizauskas, Zhixue Zhao arxiv

As large language models (LLMs) are increasing integrated into fact-checking pipelines, formal logic is often proposed as a rigorous means by which to mitigate bias, errors and hallucinations in these models' outputs. Fo…

Formal Logic

The DeepXube Software Package for Solving Pathfinding Problems with Learned Heuristic Functions and Search

2026-03-25 · Forest Agostinelli arxiv

DeepXube is a free and open-source Python package and command-line tool that seeks to automate the solution of pathfinding problems by using machine learning to learn heuristic functions that guide heuristic search algor…

Reinforcement LearningFormal Logic

The Reasoning Error About Reasoning: Why Different Types of Reasoning Require Different Representational Structures

2026-03-23 · Yiling Wu arxiv

Different types of reasoning impose different structural demands on representational systems, yet no systematic account of these demands exists across psychology, AI, and philosophy of mind. I propose a framework identif…

Causal InferenceFormal Logic

Solver-Aided Verification of Policy Compliance in Tool-Augmented LLM Agents

2026-03-20 · Cailin Winston, Claris Winston, René Just arxiv

Tool-augmented Large Language Models (TaLLMs) extend LLMs with the ability to invoke external tools, enabling them to interact with real-world environments. However, a major limitation in deploying TaLLMs in sensitive ap…

Formal Logic
1–20 / 114 다음 →