Pith. sign in

REVIEW 8 cited by

I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm

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 2408.08072 v3 pith:ZKJVMCJC submitted 2024-08-15 cs.CL

classification cs.CL
keywords textbfi-sheepalignmentllmsmodelsparadigmactivegeneration
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Large Language Models (LLMs) have achieved significant advancements, however, the common learning paradigm treats LLMs as passive information repositories, neglecting their potential for active learning and alignment. Some approaches train LLMs using their own generated synthetic data, exploring the possibility of active alignment. However, there is still a huge gap between these one-time alignment methods and the continuous automatic alignment of humans. In this paper, we introduce \textbf{I-SHEEP}, an \textbf{I}terative \textbf{S}elf-En\textbf{H}anc\textbf{E}m\textbf{E}nt \textbf{P}aradigm.This human-like paradigm enables LLMs to \textbf{continuously self-align from scratch with nothing}. Compared to the one-time alignment method Dromedary \cite{sun2023principledriven}, which refers to the first iteration in this paper, I-SHEEP can significantly enhance capacities on both Qwen and Llama models. I-SHEEP achieves a maximum relative improvement of 78.2\% in the Alpaca Eval, 24.0\% in the MT Bench, and an absolute increase of 8.88\% in the IFEval accuracy over subsequent iterations in Qwen-1.5 72B model. Additionally, I-SHEEP surpasses the base model in various standard benchmark generation tasks, achieving an average improvement of 24.77\% in code generation tasks, 12.04\% in TrivialQA, and 20.29\% in SQuAD. We also provide new insights based on the experiment results. Our codes, datasets, and models are available at \textbf{https://anonymous.4open.science/r/I-SHEEP}.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

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

  1. SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

    cs.CV 2025-07 conditional novelty 6.0 of 10

    SyncLoop jointly evolves multimodal training data and model capability through alternating SFT and RL, selecting error-prone samples to improve geometry reasoning.

  2. LLMs for Customized Marketing Content Generation and Evaluation at Scale

    cs.CL 2025-06 conditional novelty 6.0 of 10

    MarketingFM generates e-commerce ad copy with RAG and an LLM; AutoEval uses LLM-as-a-Judge plus rule checks and self-refines its prompts, with online tests showing significant clicks and impressions lifts but no signi...

  3. Aligning Instruction Tuning with Pre-training

    cs.AI 2025-01 conditional novelty 6.0 of 10

    AITP selects pre-training texts that are underrepresented relative to instruction-tuning data, rewrites them into instruction-response pairs, and improves average SFT performance on three open LLMs.

  4. Mind the Gap: Examining the Self-Improvement Capabilities of Large Language Models

    cs.CL 2024-12 conditional novelty 6.0 of 10

    A controlled, multi-family study shows the relative generation-verification gap grows with pretraining flops for stable verification methods, and iterative self-improvement saturates quickly.

  5. Preference Tree Optimization: Enhancing Goal-Oriented Dialogue with Look-Ahead Simulations

    cs.CL 2026-08 reject novelty 5.0 of 10

    Preference Tree Optimization uses look-ahead simulations scored by an AI oracle to generate DPO preference data, and the resulting Motivational Interviewing agent scores higher on that same oracle than the base model.

  6. Enterprise Large Language Model Evaluation Benchmark

    cs.AI 2025-06 reject novelty 5.0 of 10

    A 14-task enterprise LLM benchmark built mostly from GPT-4o-generated labels and scored by GPT-4o-as-judge shows open-source models closing the reasoning gap, but the dataset is not public and the evaluation is partly...

  7. Self-Improving Transformers Overcome Easy-to-Hard and Length Generalization Challenges

    cs.LG 2025-02 conditional novelty 5.0 of 10

    Iterative self-training on a model's own correct outputs, with simple length and voting filters, lets transformers generalize to far longer arithmetic and path-finding problems than they saw in training.

  8. Curiosity-Driven Reinforcement Learning from Human Feedback

    cs.CL 2025-01 conditional novelty 4.0 of 10

    Adding a prediction-error curiosity reward, masked to non-top-k tokens, improves output diversity of RLHF-trained LLMs while keeping reward-model judged quality roughly unchanged.

Pith tools