Copertina

Intuitive or Dependent? Investigating LLMs' Behavior Style to Conflicting Prompts

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Ying, Jiahao, Cao, Yixin, Xiong, Kai, He, Yidong, Cui, Long, Liu, Yongbin
Natura:	Preprint
Pubblicazione:	2023
Soggetti:	Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
di: Xiong, Kai, et al.
Pubblicazione: (2024)

Bailicai: A Domain-Optimized Retrieval-Augmented Generation Framework for Medical Applications
di: Long, Cui, et al.
Pubblicazione: (2024)

Model Utility Law: Evaluating LLMs beyond Performance through Mechanism Interpretable Metric
di: Cao, Yixin, et al.
Pubblicazione: (2025)

A + B: A General Generator-Reader Framework for Optimizing LLMs to Unleash Synergy Potential
di: Tang, Wei, et al.
Pubblicazione: (2024)

Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
di: Chen, Yixin, et al.
Pubblicazione: (2025)

Towards LLMs Robustness to Changes in Prompt Format Styles
di: Ngweta, Lilian, et al.
Pubblicazione: (2025)

Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms
di: Ying, Jiahao, et al.
Pubblicazione: (2025)

LLMs-as-Instructors: Learning from Errors Toward Automating Model Improvement
di: Ying, Jiahao, et al.
Pubblicazione: (2024)

From Latent Signals to Reflection Behavior: Tracing Meta-Cognitive Activation Trajectory in R1-Style LLMs
di: Du, Yanrui, et al.
Pubblicazione: (2026)

EffiEval: Efficient and Generalizable Model Evaluation via Capability Coverage Maximization
di: Wang, Yaoning, et al.
Pubblicazione: (2025)

Do LLMs Signal When They're Right? Evidence from Neuron Agreement
di: Chen, Kang, et al.
Pubblicazione: (2025)

Style-Compress: An LLM-Based Prompt Compression Framework Considering Task-Specific Styles
di: Pu, Xiao, et al.
Pubblicazione: (2024)

RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style
di: Liu, Yantao, et al.
Pubblicazione: (2024)

EvoWiki: Evaluating LLMs on Evolving Knowledge
di: Tang, Wei, et al.
Pubblicazione: (2024)

Disentangling Language and Culture for Evaluating Multilingual Large Language Models
di: Ying, Jiahao, et al.
Pubblicazione: (2025)

QRMeM: Unleash the Length Limitation through Question then Reflection Memory Mechanism
di: Wang, Bo, et al.
Pubblicazione: (2024)

Examining Inter-Consistency of Large Language Models Collaboration: An In-depth Analysis via Debate
di: Xiong, Kai, et al.
Pubblicazione: (2023)

Long or short CoT? Investigating Instance-level Switch of Large Reasoning Models
di: Zhang, Ruiqi, et al.
Pubblicazione: (2025)

Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs
di: Muppidi, Ananth, et al.
Pubblicazione: (2025)

A Survey of Test-Time Compute: From Intuitive Inference to Deliberate Reasoning
di: Ji, Yixin, et al.
Pubblicazione: (2025)

Harmful Prompt Laundering: Jailbreaking LLMs with Abductive Styles and Symbolic Encoding
di: Joo, Seongho, et al.
Pubblicazione: (2025)

Less Data Less Tokens: Multilingual Unification Learning for Efficient Test-Time Reasoning in LLMs
di: Chen, Kang, et al.
Pubblicazione: (2025)

The Order Effect: Investigating Prompt Sensitivity to Input Order in LLMs
di: Guan, Bryan, et al.
Pubblicazione: (2025)

Investigating the Influence of Language on Sycophantic Behavior of Multilingual LLMs
di: Aldahlawi, Bayan Abdullah, et al.
Pubblicazione: (2026)

White Men Lead, Black Women Help? Benchmarking and Mitigating Language Agency Social Biases in LLMs
di: Wan, Yixin, et al.
Pubblicazione: (2024)

Rethinking ChatGPT's Success: Usability and Cognitive Behaviors Enabled by Auto-regressive LLMs' Prompting
di: Li, Xinzhe, et al.
Pubblicazione: (2024)

Long Context vs. RAG for LLMs: An Evaluation and Revisits
di: Li, Xinze, et al.
Pubblicazione: (2024)

SETTP: Style Extraction and Tunable Inference via Dual-level Transferable Prompt Learning
di: Jin, Chunzhen, et al.
Pubblicazione: (2024)

Style-Specific Neurons for Steering LLMs in Text Style Transfer
di: Lai, Wen, et al.
Pubblicazione: (2024)

Behavior-Equivalent Token: Single-Token Replacement for Long Prompts in LLMs
di: Dong, Jiancheng, et al.
Pubblicazione: (2025)

Do Large Language Models Know Conflict? Investigating Parametric vs. Non-Parametric Knowledge of LLMs for Conflict Forecasting
di: Nemkova, Apollinaire Poli, et al.
Pubblicazione: (2025)

LLMs Are Prone to Fallacies in Causal Inference
di: Joshi, Nitish, et al.
Pubblicazione: (2024)

XFinBench: Benchmarking LLMs in Complex Financial Problem Solving and Reasoning
di: Zhang, Zhihan, et al.
Pubblicazione: (2025)

Insight Over Sight: Exploring the Vision-Knowledge Conflicts in Multimodal LLMs
di: Liu, Xiaoyuan, et al.
Pubblicazione: (2024)

Is Your Prompt Safe? Investigating Prompt Injection Attacks Against Open-Source LLMs
di: Wang, Jiawen, et al.
Pubblicazione: (2025)

Say More with Less: Understanding Prompt Learning Behaviors through Gist Compression
di: Li, Xinze, et al.
Pubblicazione: (2024)

How Large Language Models (LLMs) Extrapolate: From Guided Missiles to Guided Prompts
di: Cao, Xuenan
Pubblicazione: (2024)

Thinking Fast, Thinking Wrong: Intuitiveness Modulates LLM Counterfactual Reasoning in Policy Evaluation
di: He, Yanjie
Pubblicazione: (2026)

Why Prompt Design Matters and Works: A Complexity Analysis of Prompt Search Space in LLMs
di: Zhang, Xiang, et al.
Pubblicazione: (2025)

LLMs Can Achieve High-quality Simultaneous Machine Translation as Efficiently as Offline
di: Fu, Biao, et al.
Pubblicazione: (2025)