Copertina

Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Tutnov, Rasul, Grosnit, Antoine, Bou-Ammar, Haitham
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Why Can Large Language Models Generate Correct Chain-of-Thoughts?
di: Tutunov, Rasul, et al.
Pubblicazione: (2023)

Contextual Causal Bayesian Optimisation
di: Arsenyan, Vahan, et al.
Pubblicazione: (2023)

ShortCircuit: AlphaZero-Driven Circuit Design
di: Tsaras, Dimitrios, et al.
Pubblicazione: (2024)

SparsePO: Controlling Preference Alignment of LLMs via Sparse Token Masks
di: Christopoulou, Fenia, et al.
Pubblicazione: (2024)

Mixture of Attentions For Speculative Decoding
di: Zimmer, Matthieu, et al.
Pubblicazione: (2024)

On Almost Surely Safe Alignment of Large Language Models at Inference-Time
di: Ji, Xiaotong, et al.
Pubblicazione: (2025)

Subjective Depth and Timescale Transformers: Learning Where and When to Compute
di: Wieser, Frederico, et al.
Pubblicazione: (2025)

Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods
di: Benfeghoul, Martin, et al.
Pubblicazione: (2025)

Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
di: Ji, Xiaotong, et al.
Pubblicazione: (2026)

Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
di: Ji, Xiaotong, et al.
Pubblicazione: (2026)

Group Robust Preference Optimization in Reward-free RLHF
di: Ramesh, Shyam Sundhar, et al.
Pubblicazione: (2024)

SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
di: Hazard, Hugo, et al.
Pubblicazione: (2025)

It Takes Two: Your GRPO Is Secretly DPO
di: Wu, Yihong, et al.
Pubblicazione: (2025)

Your Transformer is Secretly Linear
di: Razzhigaev, Anton, et al.
Pubblicazione: (2024)

Risk-Controlled Lean-as-Judge for Natural-Language Mathematical Reasoning
di: Bourigault, Pauline, et al.
Pubblicazione: (2026)

Your Mixture-of-Experts LLM Is Secretly an Embedding Model For Free
di: Li, Ziyue, et al.
Pubblicazione: (2024)

The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
di: Nguyen, Tu, et al.
Pubblicazione: (2026)

The $\mathbf{Y}$-Combinator for LLMs: Solving Long-Context Rot with $λ$-Calculus
di: Roy, Amartya, et al.
Pubblicazione: (2026)

Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
di: Ramesh, Shyam Sundhar, et al.
Pubblicazione: (2026)

Al-Khwarizmi: Discovering Physical Laws with Foundation Models
di: Mower, Christopher E., et al.
Pubblicazione: (2025)

Human-inspired Episodic Memory for Infinite Context LLMs
di: Fountas, Zafeirios, et al.
Pubblicazione: (2024)

Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing
di: Tutunov, Rasul, et al.
Pubblicazione: (2025)

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data
di: Ou, Jingyang, et al.
Pubblicazione: (2024)

Self-Verified Distillation: Your Language Model Is Secretly Its Own Synthetic Data Pipeline
di: Lee, Tony, et al.
Pubblicazione: (2026)

Your Absorbing Discrete Diffusion Secretly Models the Bayesian Posterior
di: Doyle, Cooper
Pubblicazione: (2025)

Flextron: Many-in-One Flexible Large Language Model
di: Cai, Ruisi, et al.
Pubblicazione: (2024)

Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving
di: Zimmer, Matthieu, et al.
Pubblicazione: (2025)

Out of One, Many: Using Language Models to Simulate Human Samples
di: Argyle, Lisa P., et al.
Pubblicazione: (2022)

Direct Preference Optimization: Your Language Model is Secretly a Reward Model
di: Rafailov, Rafael, et al.
Pubblicazione: (2023)

Intrinsic Mutual Information as a Modulator for Preference Optimization
di: Liao, Peng, et al.
Pubblicazione: (2026)

Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity
di: Yang, Diji, et al.
Pubblicazione: (2025)

Check Your LLM's Secret Dictionary! Five Lines of Code Reveal What Your LLM Learned (Including What It Shouldn't Have)
di: Miyashita, Hisashi
Pubblicazione: (2026)

Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
di: Zhussip, Magauiya, et al.
Pubblicazione: (2025)

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation
di: Zhang, Xuan, et al.
Pubblicazione: (2024)

Efficient RLVR Training via Weighted Mutual Information Data Selection
di: Zhou, Xinyu, et al.
Pubblicazione: (2026)

BitDelta: Your Fine-Tune May Only Be Worth One Bit
di: Liu, James, et al.
Pubblicazione: (2024)

One Goal, Many Challenges: Robust Preference Optimization Amid Content-Aware and Multi-Source Noise
di: Afzali, Amirabbas, et al.
Pubblicazione: (2025)

STENCIL: Submodular Mutual Information Based Weak Supervision for Cold-Start Active Learning
di: Beck, Nathan, et al.
Pubblicazione: (2024)

Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
di: Yao, Jiashu, et al.
Pubblicazione: (2026)

Learning from Failures in Multi-Attempt Reinforcement Learning
di: Chung, Stephen, et al.
Pubblicazione: (2025)