Pith. sign in

REVIEW 5 cited by

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing

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

arxiv 2406.05534 v1 pith:F5ZUBTTB submitted 2024-06-08 cs.AI cs.CLcs.LG

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing

classification cs.AI cs.CLcs.LG
keywords onlinealignmentchasingoptimizationpreferencecompetitioncontinualcross-domain
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Direct Preference Optimization (DPO) improves the alignment of large language models (LLMs) with human values by training directly on human preference datasets, eliminating the need for reward models. However, due to the presence of cross-domain human preferences, direct continual training can lead to catastrophic forgetting, limiting DPO's performance and efficiency. Inspired by intraspecific competition driving species evolution, we propose a Online Fast-Slow chasing DPO (OFS-DPO) for preference alignment, simulating competition through fast and slow chasing among models to facilitate rapid adaptation. Specifically, we first derive the regret upper bound for online learning, validating our motivation with a min-max optimization pattern. Based on this, we introduce two identical modules using Low-rank Adaptive (LoRA) with different optimization speeds to simulate intraspecific competition, and propose a new regularization term to guide their learning. To further mitigate catastrophic forgetting in cross-domain scenarios, we extend the OFS-DPO with LoRA modules combination strategy, resulting in the Cross domain Online Fast-Slow chasing DPO (COFS-DPO). This method leverages linear combinations of fast modules parameters from different task domains, fully utilizing historical information to achive continual value alignment. Experimental results show that OFS-DPO outperforms DPO in in-domain alignment, while COFS-DPO excels in cross-domain continual learning scenarios.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization

    cs.LG 2026-05 unverdicted novelty 7.0

    PBSD derives a reward-reweighted teacher distribution as the analytic optimum of a reward-regularized objective, yielding better stability and performance than KL-based self-distillation on math reasoning and tool-use tasks.

  2. Test-Time Scaling via Error Localization

    cs.LG 2026-07 conditional novelty 6.0

    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.

  3. Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning

    cs.CL 2026-04 accept novelty 5.0

    LLM post-training is unified as off-policy or on-policy interventions that expand support for useful behaviors, reshape policies within reachable states, or consolidate behavior across training stages.

  4. Gene-R1: Reasoning with Data-Augmented Lightweight LLMs for Gene Set Analysis

    q-bio.GN 2025-09 conditional novelty 5.0

    Gene-R1 combines domain pre-training, GPT-o1 distilled reasoning examples, and GRPO reinforcement learning so lightweight Llama models match commercial LLMs on gene set analysis.

  5. RPO-PDT: Demonstrating Role-Play-Based Knowledge Adaptation for Student Support Dialogue (Demonstration System)

    cs.RO 2026-06 unverdicted novelty 4.0

    RPO-PDT demonstrates a role-play-based, retrieval-grounded system for adaptive, policy-constrained student support dialogue with reverse-roleplay for strategy memory.