Copertina

False Fixed Points: Kantian Feedback, Stable Miscalibration, and Representational Compression in LLMs

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Okutomi, Akira
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Artificial Intelligence Computation and Language Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Probabilities of Chat LLMs Are Miscalibrated but Still Predict Correctness on Multiple-Choice Q&A
di: Plaut, Benjamin, et al.
Pubblicazione: (2024)

Large Language Models are Miscalibrated In-Context Learners
di: Li, Chengzu, et al.
Pubblicazione: (2023)

Non-Halting Queries: Exploiting Fixed Points in LLMs
di: Hammouri, Ghaith, et al.
Pubblicazione: (2024)

On Overcoming Miscalibrated Conversational Priors in LLM-based Chatbots
di: Herlihy, Christine, et al.
Pubblicazione: (2024)

Can We Count on LLMs? The Fixed-Effect Fallacy and Claims of GPT-4 Capabilities
di: Ball, Thomas, et al.
Pubblicazione: (2024)

Aligning Tree-Search Policies with Fixed Token Budgets in Test-Time Scaling of LLMs
di: Miyamoto, Sora, et al.
Pubblicazione: (2026)

Semantic Refinement with LLMs for Graph Representations
di: Thapaliya, Safal, et al.
Pubblicazione: (2025)

Beyond Benchmarks: On The False Promise of AI Regulation
di: Stanovsky, Gabriel, et al.
Pubblicazione: (2025)

GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback
di: Xu, Ruiyao, et al.
Pubblicazione: (2026)

RLPF: Reinforcement Learning from Prediction Feedback for User Summarization with LLMs
di: Wu, Jiaxing, et al.
Pubblicazione: (2024)

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
di: Wang, Xingyao, et al.
Pubblicazione: (2023)

Adapting LLMs for Efficient Context Processing through Soft Prompt Compression
di: Wang, Cangqing, et al.
Pubblicazione: (2024)

Optimizing LLMs for Resource-Constrained Environments: A Survey of Model Compression Techniques
di: Girija, Sanjay Surendranath, et al.
Pubblicazione: (2025)

HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs
di: Yang, Dongquan, et al.
Pubblicazione: (2025)

Enhancing Delta Compression in LLMs via SVD-based Quantization Error Minimization
di: Xiong, Boya, et al.
Pubblicazione: (2025)

RLHF Deciphered: A Critical Analysis of Reinforcement Learning from Human Feedback for LLMs
di: Chaudhari, Shreyas, et al.
Pubblicazione: (2024)

Overthinking the Truth: Understanding how Language Models Process False Demonstrations
di: Halawi, Danny, et al.
Pubblicazione: (2023)

Self-Distillation as a Performance Recovery Mechanism for LLMs: Counteracting Compression and Catastrophic Forgetting
di: Liu, Chi, et al.
Pubblicazione: (2026)

Shared Lexical Task Representations Explain Behavioral Variability In LLMs
di: Yang, Zhuonan, et al.
Pubblicazione: (2026)

TinyV: Reducing False Negatives in Verification Improves RL for LLM Reasoning
di: Xu, Zhangchen, et al.
Pubblicazione: (2025)

Large Language Models are Skeptics: False Negative Problem of Input-conflicting Hallucination
di: Song, Jongyoon, et al.
Pubblicazione: (2024)

CHAI for LLMs: Improving Code-Mixed Translation in Large Language Models through Reinforcement Learning with AI Feedback
di: Zhang, Wenbo, et al.
Pubblicazione: (2024)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
di: Siu, Vincent, et al.
Pubblicazione: (2025)

From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMs
di: Rezazadeh, Alireza, et al.
Pubblicazione: (2024)

The Effectiveness of LLMs as Annotators: A Comparative Overview and Empirical Analysis of Direct Representation
di: Pavlovic, Maja, et al.
Pubblicazione: (2024)

Sign Lock-In: Randomly Initialized Weight Signs Persist and Bottleneck Sub-Bit Model Compression
di: Sakai, Akira, et al.
Pubblicazione: (2026)

RLSF: Fine-tuning LLMs via Symbolic Feedback
di: Jha, Piyush, et al.
Pubblicazione: (2024)

LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings
di: Wang, Duo, et al.
Pubblicazione: (2024)

UltraFeedback: Boosting Language Models with Scaled AI Feedback
di: Cui, Ganqu, et al.
Pubblicazione: (2023)

T-FREE: Subword Tokenizer-Free Generative LLMs via Sparse Representations for Memory-Efficient Embeddings
di: Deiseroth, Björn, et al.
Pubblicazione: (2024)

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy
di: Zhang, Rongzhi, et al.
Pubblicazione: (2024)

Projected Compression: Trainable Projection for Efficient Transformer Compression
di: Stefaniak, Maciej, et al.
Pubblicazione: (2025)

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards
di: Wang, Zhilin, et al.
Pubblicazione: (2025)

Balanced Aggregation: Understanding and Fixing Aggregation Bias in GRPO
di: Zeng, Zhiyuan, et al.
Pubblicazione: (2026)

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
di: Lee, Harrison, et al.
Pubblicazione: (2023)

Reinforcement Learning with Backtracking Feedback
di: Sel, Bilgehan, et al.
Pubblicazione: (2026)

Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
di: Fu, Yuqian, et al.
Pubblicazione: (2026)

Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
di: Pal, Arka, et al.
Pubblicazione: (2024)

Textual Unlearning Gives a False Sense of Unlearning
di: Du, Jiacheng, et al.
Pubblicazione: (2024)

SELF: Self-Evolution with Language Feedback
di: Lu, Jianqiao, et al.
Pubblicazione: (2023)