REVIEW 9 cited by
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
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
This paper studies post-training large language models (LLMs) using preference feedback from a powerful oracle to help a model iteratively improve over itself. The typical approach for post-training LLMs involves Reinforcement Learning from Human Feedback (RLHF), which traditionally separates reward learning and subsequent policy optimization. However, such a reward maximization approach is limited by the nature of "point-wise" rewards (such as Bradley-Terry model), which fails to express complex intransitive or cyclic preference relations. While advances on RLHF show reward learning and policy optimization can be merged into a single contrastive objective for stability, they yet still remain tethered to the reward maximization framework. Recently, a new wave of research sidesteps the reward maximization presumptions in favor of directly optimizing over "pair-wise" or general preferences. In this paper, we introduce Direct Nash Optimization (DNO), a provable and scalable algorithm that marries the simplicity and stability of contrastive learning with theoretical generality from optimizing general preferences. Because DNO is a batched on-policy algorithm using a regression-based objective, its implementation is straightforward and efficient. Moreover, DNO enjoys monotonic improvement across iterations that help it improve even over a strong teacher (such as GPT-4). In our experiments, a resulting 7B parameter Orca-2.5 model aligned by DNO achieves the state-of-the-art win-rate against GPT-4-Turbo of 33% on AlpacaEval 2.0 (even after controlling for response length), an absolute gain of 26% (7% to 33%) over the initializing model. It outperforms models with far more parameters, including Mistral Large, Self-Rewarding LM (70B parameters), and older versions of GPT-4.
Forward citations
Cited by 9 Pith papers
-
Sign-SZPO: Provable Preference-based Reinforcement Learning with an Unknown Link Function
ZSPO provably converges to a stationary policy using only the sign of preference feedback, without knowing the link function between preferences and rewards.
-
Debiasing Online Preference Learning via Preference Feature Preservation
PFP preserves the distribution of human preference features during online preference learning by mapping each new instruction to a feature set, converting it to system prompts, and training with DPO.
-
Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment
Post-training alignment on synthetic graph data yields statistically significant gains on some real-world implicit-graph tasks, but gains are inconsistent and multi-step reasoning remains fragile.
-
Square$\chi$PO: Differentially Private and Robust $\chi^2$-Preference Optimization in Offline Direct Alignment
SquareχPO, a square-loss variant of χPO, achieves optimal 1/sqrt(n) suboptimality under label privacy and Huber corruption for offline direct alignment with general function classes.
-
Learning a Pessimistic Reward Model in RLHF
Pessimistic fine-tuning of reward models against rejection-sampling policies lets RLHF agents optimize greedily without KL regularization and still avoid reward hacking.
-
MPO: Multilingual Safety Alignment via Reward Gap Optimization
MPO reduces jailbreak success in multilingual LLMs by regressing target-language reward gaps onto the English reward gap, outperforming DPO and related methods while preserving utility.
-
Reward Shaping for (Inference-Time) Alignment: A Stackelberg Game Perspective
The optimal reward for KL-regularized LLM alignment is a threshold function—reward B above a prompt-dependent cutoff, 0 below—which can be estimated from base-model samples and integrated into decoding-time alignment.
-
Improved Bounds for Private and Robust Alignment
Private MLE log loss is near-optimal for alignment, and square-loss alignment tolerates corruption at the optimal linear rate, including in online exploration.
-
Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers
A taxonomy-based survey of bidirectional game theory and LLM research, spanning evaluation, alignment, economic competition, and LLM-driven game solving.
Discussion (0). Sign in to comment.