Pith. sign in

REVIEW 4 cited by

Shepherd: A Critic for Language Model Generation

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 2308.04592 v1 pith:55IP5IEN submitted 2023-08-08 cs.CL cs.AI

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

As large language models improve, there is increasing interest in techniques that leverage these models' capabilities to refine their own outputs. In this work, we introduce Shepherd, a language model specifically tuned to critique responses and suggest refinements, extending beyond the capabilities of an untuned model to identify diverse errors and provide suggestions to remedy them. At the core of our approach is a high quality feedback dataset, which we curate from community feedback and human annotations. Even though Shepherd is small (7B parameters), its critiques are either equivalent or preferred to those from established models including ChatGPT. Using GPT-4 for evaluation, Shepherd reaches an average win-rate of 53-87% compared to competitive alternatives. In human evaluation, Shepherd strictly outperforms other models and on average closely ties with ChatGPT.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

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

  1. Understanding Human Limits in Pattern Recognition: A Computational Model of Sequential Reasoning in Rock, Paper, Scissors

    q-bio.NC 2025-07 conditional novelty 6.0 of 10

    An LLM agent reproduces human rock-paper-scissors pattern learning, and interventions suggest that hypothesis generation, not evaluation, is the main cognitive bottleneck.

  2. SkillVerse : Assessing and Enhancing LLMs with Tree Evaluation

    cs.CL 2025-05 conditional novelty 6.0 of 10

    SkillVerse clusters LLM critiques into a dendrogram of skills and uses it to improve in-context learning and predict unseen model weaknesses.

  3. Meta-Learned Reward Shaping for Reinforcement Learning from Human Feedback

    cs.LG 2026-07 reject novelty 5.0 of 10

    Training a small multi-task reward-shaping network and adding it to the RLHF reward is claimed to improve LLaMA-3-8B alignment across four benchmarks, but the supporting theory is not established.

  4. Exchange of Perspective Prompting Enhances Reasoning in Large Language Models

    cs.CL 2025-06 conditional novelty 5.0 of 10

    A two-branch prompting method that exchanges answers between an original math question and a paraphrased version improves accuracy on several math benchmarks, but the gain is not separated from the extra compute or ru...

Pith tools