Copertina

Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Li, Bangzheng, Zhou, Ben, Wang, Fei, Fu, Xingyu, Roth, Dan, Chen, Muhao
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

FamiCom: Further Demystifying Prompts for Language Models with Task-Agnostic Performance Estimation
di: Li, Bangzheng, et al.
Pubblicazione: (2024)

Break the Chain: Large Language Models Can be Shortcut Reasoners
di: Ding, Mengru, et al.
Pubblicazione: (2024)

Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection
di: Li, Bangzheng, et al.
Pubblicazione: (2025)

R-Horizon: How Far Can Your Large Reasoning Model Really Go in Breadth and Depth?
di: Lu, Yi, et al.
Pubblicazione: (2025)

Red Teaming Language Models for Processing Contradictory Dialogues
di: Wen, Xiaofei, et al.
Pubblicazione: (2024)

Financial Named Entity Recognition: How Far Can LLM Go?
di: Lu, Yi-Te, et al.
Pubblicazione: (2025)

How Far Can In-Context Alignment Go? Exploring the State of In-Context Alignment
di: Huang, Heyan, et al.
Pubblicazione: (2024)

From Shortcuts to Triggers: Backdoor Defense with Denoised PoE
di: Liu, Qin, et al.
Pubblicazione: (2023)

AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?
di: Karmakar, Ranit, et al.
Pubblicazione: (2026)

BLINK: Multimodal Large Language Models Can See but Not Perceive
di: Fu, Xingyu, et al.
Pubblicazione: (2024)

Dynamic Clue Bottlenecks: Towards Interpretable-by-Design Visual Question Answering
di: Fu, Xingyu, et al.
Pubblicazione: (2023)

RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?
di: Góngora, Santiago, et al.
Pubblicazione: (2025)

Code Execution as Grounded Supervision for LLM Reasoning
di: Jung, Dongwon, et al.
Pubblicazione: (2025)

How Far Are We from Optimal Reasoning Efficiency?
di: Gao, Jiaxuan, et al.
Pubblicazione: (2025)

OS-MAP: How Far Can Computer-Using Agents Go in Breadth and Depth?
di: Chen, Xuetian, et al.
Pubblicazione: (2025)

Commonsense-T2I Challenge: Can Text-to-Image Generation Models Understand Commonsense?
di: Fu, Xingyu, et al.
Pubblicazione: (2024)

Active Layer-Contrastive Decoding Reduces Hallucination in Large Language Model Generation
di: Zhang, Hongxiang, et al.
Pubblicazione: (2025)

Mitigating Shortcut Reasoning in Language Models: A Gradient-Aware Training Approach
di: Cao, Hongyu, et al.
Pubblicazione: (2026)

LLMs for Relational Reasoning: How Far are We?
di: Li, Zhiming, et al.
Pubblicazione: (2024)

MotiveBench: How Far Are We From Human-Like Motivational Reasoning in Large Language Models?
di: Yong, Xixian, et al.
Pubblicazione: (2025)

Unbiased Visual Reasoning with Controlled Visual Inputs
di: Li, Zhaonan, et al.
Pubblicazione: (2025)

Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection
di: Chen, Kedi, et al.
Pubblicazione: (2025)

SocREval: Large Language Models with the Socratic Method for Reference-Free Reasoning Evaluation
di: He, Hangfeng, et al.
Pubblicazione: (2023)

Large Language Models for Predictive Analysis: How Far Are They?
di: Chen, Qin, et al.
Pubblicazione: (2025)

Affective and Dynamic Beam Search for Story Generation
di: Huang, Tenghao, et al.
Pubblicazione: (2023)

The AI Co-Ethnographer: How Far Can Automation Take Qualitative Research?
di: Retkowski, Fabian, et al.
Pubblicazione: (2025)

Lie to Me: How Faithful Is Chain-of-Thought Reasoning in Reasoning Models?
di: Young, Richard J.
Pubblicazione: (2026)

The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
di: Kim, Dueun, et al.
Pubblicazione: (2026)

How Fragile is Relation Extraction under Entity Replacements?
di: Wang, Yiwei, et al.
Pubblicazione: (2023)

SudoLM: Learning Access Control of Parametric Knowledge with Authorization Alignment
di: Liu, Qin, et al.
Pubblicazione: (2024)

How Trustworthy are Open-Source LLMs? An Assessment under Malicious Demonstrations Shows their Vulnerabilities
di: Mo, Lingbo, et al.
Pubblicazione: (2023)

The Self-Improvement Paradox: Can Language Models Bootstrap Reasoning Capabilities without External Scaffolding?
di: Sun, Yutao, et al.
Pubblicazione: (2025)

The Point of No Return: Counterfactual Localization of Deceptive Commitment in Language-Model Reasoning
di: Merrill, Scott, et al.
Pubblicazione: (2026)

Shattering the Shortcut: A Topology-Regularized Benchmark for Multi-hop Medical Reasoning in LLMs
di: Zi, Xing, et al.
Pubblicazione: (2026)

Getting Sick After Seeing a Doctor? Diagnosing and Mitigating Knowledge Conflicts in Event Temporal Reasoning
di: Fang, Tianqing, et al.
Pubblicazione: (2023)

How does Chain of Thought Think? Mechanistic Interpretability of Chain-of-Thought Reasoning with Sparse Autoencoding
di: Chen, Xi, et al.
Pubblicazione: (2025)

How Small Can You Go? Compact Language Models for On-Device Critical Error Detection in Machine Translation
di: Chopra, Muskaan, et al.
Pubblicazione: (2025)

Knowing the Facts but Choosing the Shortcut: Understanding How Large Language Models Compare Entities
di: Lehmann, Hans Hergen, et al.
Pubblicazione: (2025)

ReEval: Automatic Hallucination Evaluation for Retrieval-Augmented Large Language Models via Transferable Adversarial Attacks
di: Yu, Xiaodong, et al.
Pubblicazione: (2023)

Towards Long Context Hallucination Detection
di: Liu, Siyi, et al.
Pubblicazione: (2025)