REVIEW 17 cited by
RRHF: Rank Responses to Align Language Models with Human Feedback without tears
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Reinforcement Learning from Human Feedback (RLHF) facilitates the alignment of large language models with human preferences, significantly enhancing the quality of interactions between humans and models. InstructGPT implements RLHF through several stages, including Supervised Fine-Tuning (SFT), reward model training, and Proximal Policy Optimization (PPO). However, PPO is sensitive to hyperparameters and requires multiple models in its standard implementation, making it hard to train and scale up to larger parameter counts. In contrast, we propose a novel learning paradigm called RRHF, which scores sampled responses from different sources via a logarithm of conditional probabilities and learns to align these probabilities with human preferences through ranking loss. RRHF can leverage sampled responses from various sources including the model responses from itself, other large language model responses, and human expert responses to learn to rank them. RRHF only needs 1 to 2 models during tuning and can efficiently align language models with human preferences robustly without complex hyperparameter tuning. Additionally, RRHF can be considered an extension of SFT and reward model training while being simpler than PPO in terms of coding, model counts, and hyperparameters. We evaluate RRHF on the Helpful and Harmless dataset, demonstrating comparable alignment performance with PPO by reward model score and human labeling. Extensive experiments show that the performance of RRHF is highly related to sampling quality which suggests RRHF is a best-of-n learner. Codes available at https://github.com/GanjinZero/RRHF.
Forward citations
Cited by 17 Pith papers
-
Test-Time Scaling via Error Localization
TTEL uses feedback-induced token probability drops to localize the first error in a failed reasoning trace and branch a new generation from that prefix, improving pass@k per token on coding and math benchmarks.
-
Every Sample Counts: Supervised Fine-Tuning of Language Models with Pointwise Constraints
Pointwise constrained fine-tuning via sample-wise augmented Lagrangians and learned relaxations reduces tail constraint violations across safety, tool-calling, and re-ranking while preserving average task performance.
-
Multi-Turn On-Policy Distillation with Prefix Replay
ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.
-
SCOPE and SCION: A Benchmark and an Auditable Reference Pipeline for Schema Induction and Fusion from Text
A 24-dataset benchmark for inducing schema graphs from raw text, plus an auditable LLM-based pipeline that reports the highest scores on the benchmark's four schema-similarity metrics.
-
RLearner-LLM: Balancing Logical Grounding and Fluency in Large Language Models via Hybrid Direct Preference Optimization
RLearner-LLM's Hybrid-DPO fuses DeBERTa NLI and LLM verifier scores to deliver up to 6x higher NLI entailment than standard SFT while preserving answer coverage across academic domains.
-
Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards
MAHALO aligns LLMs to multiple objectives in one model via per-objective action heads and PRM-guided decoding, improving math, value, and tutoring metrics jointly.
-
Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security
An iterative attacker-defender reinforcement learning method that makes a multimodal LLM refuse more jailbreak prompts without over-refusing ordinary queries.
-
Enhancing Safe and Controllable Protein Generation via Knowledge Preference Optimization
A knowledge-graph-guided preference optimization framework that fine-tunes protein language models to generate fewer sequences similar to known harmful proteins.
-
Flipping Knowledge Distillation: Leveraging Small Models' Expertise to Enhance LLMs in Text Matching
A flipped distillation method lets a decoder-only LLM learn text-matching similarity from a smaller encoder teacher through LoRA and a margin-aware contrastive loss, improving matching accuracy and online FAQ retrieval.
-
From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation
ProxyReward trains long-form generation models by rewarding how well an AI judge can answer generated yes/no questions about the response, improving open-source models on ProxyQA.
-
Quo Vadis, World Modeling?
An agent-centric reframing of world modeling, replacing physical state prediction with 'information transitions' organized into six proxy functions and three empowerment levels.
-
Beyond Surface-Level Detection: Towards Cognitive-Driven Defense Against Jailbreak Attacks via Meta-Operations Reasoning
A jailbreak defense that reasons about hidden manipulations in attack prompts, trained with supervised fine-tuning plus entropy-guided reinforcement learning, generalizes to attacks never seen in training.
-
Activation Reward Models for Few-Shot Model Alignment
Mean attention-head activations from a few labeled examples, injected into selected heads, turn a frozen vision-language model into a few-shot reward model that beats prompting and scoring baselines and a new reward-h...
-
Value-Free Policy Optimization via Reward Partitioning
RPO regresses the policy log-ratio against rewards centered by an empirical partition function estimated from same-prompt responses, removing the value network and reporting improved alignment, diversity, and lower toxicity.
-
PKG-DPO: Optimizing Domain-Specific AI systems with Physics Knowledge Graphs and Direct Preference Optimization
A physics knowledge graph plus Direct Preference Optimization reduces physically invalid AI recommendations in welding by 17% over knowledge-graph-only DPO, but the evidence is weakened by circular evaluation and no p...
-
Alignment and Safety in Large Language Models: Safety Mechanisms, Training Paradigms, and Emerging Challenges
A broad survey of LLM alignment that catalogs objectives, benchmarks, SFT/RLHF/DPO methods, and safety challenges, without contributing new experimental or theoretical results.
-
Inverse Reinforcement Learning Meets Large Language Model Post-Training: Basics, Advances, and Opportunities
A tutorial reviewing LLM alignment through the lens of inverse reinforcement learning, arguing that neural reward models learned from human data are central to post-training.
Discussion (0). Sign in to comment.