P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
hub
Slic-hf: Sequence likelihood calibration with human feedback
25 Pith papers cite this work. Polarity classification is still indexing.
25
Pith papers citing it
hub tools
representative citing papers
DPO-RLHF equivalence holds only conditionally on the optimal policy preferring human-preferred responses; otherwise DPO optimizes relative advantage and can prefer worse outputs, addressed by introducing CPO.
The paper derives a Θ(1/√(n log n)) hypothesis testing rate under strategic annotator behavior and shows that high-certainty, format-similar golden questions better reveal annotation quality than standard checks.
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
ViPSy constructs policy-aligned and visually grounded preference pairs for VLMs via visual cues from image variants, yielding SOTA hallucination reductions of 35.7% on AMBER and 24.5% on Object HalBench.
Emo-LiPO applies listwise preference optimization to model global emotion intensity ordering in LLM TTS, yielding better accuracy and controllability than supervised or DPO baselines on a new multi-speaker dataset.
MARD-7B outperforms baselines and GPT-4o on novel drug pairs for mechanism-level DDI prediction via a new distillation pipeline with verifiable process rewards and releases all resources.
AttentionPO weights tokens in DPO using LLM attention as a pairwise judge, yielding better results on AlpacaEval, MT-Bench, and ArenaHard than prior preference optimization methods.
CROP uses compositional reasoning and expert preference alignment in VLMs to produce aesthetic crops that match human experts more closely than previous methods.
Anomaly Preference Optimization reformulates anomaly image generation as preference learning using real anomalies for implicit alignment signals from denoising trajectories plus a time-aware capacity allocation module.
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
A single attacker can use strategic upvoting and downvoting on language model outputs to inject facts, security flaws, or fake news that persist in the model for all users after preference tuning.
Develops self-consistency monitoring for preference annotators and derives sample-complexity bounds showing linear contracts achieve near-ideal performance faster than binary ones under continuous actions.
PGT optimizes latent goal embeddings for frozen policies via trajectory-level preference objectives, reporting 72-81.6% relative gains on 17 Minecraft tasks and 13.4% better OOD performance than fine-tuning.
Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-world booking scenarios.
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
Generated video latents are pushed toward a shell-shaped manifold fitted to high-quality SFT video patches, producing a dense reward that reduces blur, over-smoothing, and motion artifacts in text-to-video models.
S-SPPO stabilizes SPPO via semantic calibration in supervision and representation spaces, reporting 52.19% win rate on AlpacaEval 2.0 with Llama-3-8B.
DEPO constructs uncertainty bonuses from historical data for exploration in online RLHF and provides a data-dependent regret bound that adapts to task hardness.
POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context length by up to 10x on benchmarks.
Derives SimPO from MaxEnt RL and reports that MaxEnt RL in online RLHF exhibits frequent overoptimization and unstable KL dynamics across scales, unlike stable KL-constrained baselines.
A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.
An expository book that systematically presents RLHF methods, from reward modeling to direct alignment algorithms, aimed at readers with quantitative backgrounds.
citing papers explorer
-
P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization
P²-DPO generates on-policy preference pairs targeting focus-and-enhance perception and visual robustness, combined with a calibration loss, to reduce hallucinations in LVLMs more effectively than human-feedback baselines.
-
Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment
DPO-RLHF equivalence holds only conditionally on the optimal policy preferring human-preferred responses; otherwise DPO optimizes relative advantage and can prefer worse outputs, addressed by introducing CPO.
-
Incentivizing High-Quality Human Annotations with Golden Questions
The paper derives a Θ(1/√(n log n)) hypothesis testing rate under strategic annotator behavior and shows that high-certainty, format-similar golden questions better reveal annotation quality than standard checks.
-
KTO: Model Alignment as Prospect Theoretic Optimization
KTO aligns LLMs by directly maximizing prospect-theoretic utility on binary signals and matches or exceeds preference-based methods like DPO from 1B to 30B parameters.
-
Self-Rewarding Language Models
Iterative self-rewarding via LLM-as-Judge in DPO training on Llama 2 70B improves instruction following and self-evaluation, outperforming GPT-4 on AlpacaEval 2.0.
-
Vision-driven Preference Synthesis for Mitigating Hallucinations in VLMs
ViPSy constructs policy-aligned and visually grounded preference pairs for VLMs via visual cues from image variants, yielding SOTA hallucination reductions of 35.7% on AMBER and 24.5% on Object HalBench.
-
Emo-LiPO: Listwise Preference Optimization for Fine-Grained Emotion Intensity Control in LLM-based Text-to-Speech
Emo-LiPO applies listwise preference optimization to model global emotion intensity ordering in LLM TTS, yielding better accuracy and controllability than supervised or DPO baselines on a new multi-speaker dataset.
-
MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction Prediction
MARD-7B outperforms baselines and GPT-4o on novel drug pairs for mechanism-level DDI prediction via a new distillation pipeline with verifiable process rewards and releases all resources.
-
Token-weighted Direct Preference Optimization with Attention
AttentionPO weights tokens in DPO using LLM attention as a pairwise judge, yielding better results on AlpacaEval, MT-Bench, and ArenaHard than prior preference optimization methods.
-
CROP: Expert-Aligned Image Cropping via Compositional Reasoning and Optimizing Preference
CROP uses compositional reasoning and expert preference alignment in VLMs to produce aesthetic crops that match human experts more closely than previous methods.
-
Anomaly-Preference Image Generation
Anomaly Preference Optimization reformulates anomaly image generation as preference learning using real anomalies for implicit alignment signals from denoising trajectories plus a time-aware capacity allocation module.
-
Representation-Guided Parameter-Efficient LLM Unlearning
REGLU guides LoRA-based unlearning via representation subspaces and orthogonal regularization to outperform prior methods on forget-retain trade-off in LLM benchmarks.
-
LLM Hypnosis: Exploiting User Feedback for Unauthorized Knowledge Injection to All Users
A single attacker can use strategic upvoting and downvoting on language model outputs to inject facts, security flaws, or fake news that persist in the model for all users after preference tuning.
-
How Humans Help LLMs: Assessing and Incentivizing Human Preference Annotators
Develops self-consistency monitoring for preference annotators and derives sample-complexity bounds showing linear contracts achieve near-ideal performance faster than binary ones under continuous actions.
-
Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
PGT optimizes latent goal embeddings for frozen policies via trajectory-level preference objectives, reporting 72-81.6% relative gains on 17 Minecraft tasks and 13.4% better OOD performance than fine-tuning.
-
Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents
Agent Q integrates MCTS-guided search, self-critique, and off-policy DPO to train LLM agents that outperform behavior cloning and reinforced fine-tuning baselines in WebShop and achieve up to 95.4% success in real-world booking scenarios.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video Generation
Generated video latents are pushed toward a shell-shaped manifold fitted to high-quality SFT video patches, producing a dense reward that reduces blur, over-smoothing, and motion artifacts in text-to-video models.
-
S-SPPO: Semantic-Calibrated Self-Play Preference Optimization
S-SPPO stabilizes SPPO via semantic calibration in supervision and representation spaces, reporting 52.19% win rate on AlpacaEval 2.0 with Llama-3-8B.
-
Data-dependent Exploration for Online Reinforcement Learning from Human Feedback
DEPO constructs uncertainty bonuses from historical data for exploration in online RLHF and provides a data-dependent regret bound that adapts to task hardness.
-
POPI: Personalizing LLMs via Optimized Natural Language Preference Inference
POPI distills user preferences into reusable natural-language summaries via a shared inference model and conditions a generator on them, trained jointly with RL to improve personalization quality while cutting context length by up to 10x on benchmarks.
-
Failure Modes of Maximum Entropy RLHF
Derives SimPO from MaxEnt RL and reports that MaxEnt RL in online RLHF exhibits frequent overoptimization and unstable KL dynamics across scales, unlike stable KL-constrained baselines.
-
The Hitchhiker's Guide to Agentic AI: From Foundations to Systems
A survey-style reference book mapping the full agentic-AI stack from transformer internals to production deployment, with no new research result.
-
Reinforcement Learning from Human Feedback
An expository book that systematically presents RLHF methods, from reward modeling to direct alignment algorithms, aimed at readers with quantitative backgrounds.
- Mind the Gap: Structure-Aware Consistency in Preference Learning