Pith. sign in

REVIEW 6 cited by

Self-Exploring Language Models: Active Preference Elicitation for Online Alignment

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 2405.19332 v3 pith:JXVYNV2N submitted 2024-05-29 cs.LG cs.AI

classification cs.LGcs.AI
keywords modelslanguageselmllmsobjectivepreferencerewardalignment
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Preference optimization, particularly through Reinforcement Learning from Human Feedback (RLHF), has achieved significant success in aligning Large Language Models (LLMs) to adhere to human intentions. Unlike offline alignment with a fixed dataset, online feedback collection from humans or AI on model generations typically leads to more capable reward models and better-aligned LLMs through an iterative process. However, achieving a globally accurate reward model requires systematic exploration to generate diverse responses that span the vast space of natural language. Random sampling from standard reward-maximizing LLMs alone is insufficient to fulfill this requirement. To address this issue, we propose a bilevel objective optimistically biased towards potentially high-reward responses to actively explore out-of-distribution regions. By solving the inner-level problem with the reparameterized reward function, the resulting algorithm, named Self-Exploring Language Models (SELM), eliminates the need for a separate RM and iteratively updates the LLM with a straightforward objective. Compared to Direct Preference Optimization (DPO), the SELM objective reduces indiscriminate favor of unseen extrapolations and enhances exploration efficiency. Our experimental results demonstrate that when fine-tuned on Zephyr-7B-SFT and Llama-3-8B-Instruct models, SELM significantly boosts the performance on instruction-following benchmarks such as MT-Bench and AlpacaEval 2.0, as well as various standard academic benchmarks in different settings. Our code and models are available at https://github.com/shenao-zhang/SELM.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 6 Pith papers

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

  1. Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits

    cs.LG 2025-05 conditional novelty 7.0 of 10

    Outcome-based online RL is tractable under coverability with general function approximation, but there are MDPs where trajectory-level feedback costs exponentially more samples than per-step feedback.

  2. Outcome-based Exploration for LLM Reasoning

    cs.LG 2025-09 conditional novelty 6.0 of 10

    Outcome-based exploration bonuses (UCB-Con and Batch) improve pass@1 and pass@32 for LLM math reasoning while slowing diversity collapse, supported by a bandit model with a strong generalization assumption.

  3. SharedRep-RLHF: A Shared Representation Approach to RLHF with Diverse Preferences

    cs.LG 2025-09 reject novelty 6.0 of 10

    SharedRep-RLHF learns a shared preference representation across groups to improve worst-case reward estimates for minority annotators, but the theoretical guarantees are undermined by proof errors.

  4. Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

    cs.LG 2025-06 conditional novelty 6.0 of 10

    VAC is a new actor-critic method with a single optimistic objective and a provably near-optimal regret bound in linear Markov decision processes.

  5. Learning a Pessimistic Reward Model in RLHF

    cs.LG 2025-05 reject novelty 6.0 of 10

    Pessimistic fine-tuning of reward models against rejection-sampling policies lets RLHF agents optimize greedily without KL regularization and still avoid reward hacking.

  6. MEMETRON: Metaheuristic Mechanisms for Test-time Response Optimization of Large Language Models

    cs.CL 2025-06 reject novelty 5.0 of 10

    A memetic algorithm that applies genetic search and simulated annealing, with LLMs as the variation operators, to improve LLM responses with respect to an arbitrary reward function at inference time.

Pith tools