Pith. sign in

REVIEW 4 cited by

Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Together

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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 2407.10930 v2 pith:4GNRTZIZ submitted 2024-07-15 cs.CL cs.AIcs.LG

Dilara Soylu , Christopher Potts , Omar Khattab This is my paper · ORCID
classification cs.CLcs.AIcs.LG
keywords promptoptimizationoptimizestrategiessystemsweightsaloneassociated
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Natural Language Processing (NLP) systems are increasingly taking the form of sophisticated modular pipelines, e.g., Retrieval Augmented Generation (RAG), where each module may involve a distinct Language Model (LM) and an associated prompt template. These compound systems often lack intermediate labels or gradient flow to optimize each module, making their end-to-end optimization challenging. Here we seek strategies to optimize both the module-level LM weights and the associated prompt templates of such systems to maximize a downstream task metric. We propose for the first time combining the weight and prompt optimization strategies to optimize a modular LM pipeline by alternating between the two to get the same LM to teach itself. In experiments with multi-hop QA, mathematical reasoning, and feature-based classification using mistral-7b, llama-2-7b, and llama-3-8b, these BetterTogether strategies optimizing the weights and prompts of a pipeline together outperform directly optimizing weights alone and prompts alone by up to 60% and 6%, respectively, on average across LMs and tasks. BetterTogether optimizer is released in DSPy at http://dspy.ai

Discussion (0). Continue with ORCID 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. COSMOS: Predictable and Cost-Effective Adaptation of LLMs

    cs.LG 2025-04 conditional novelty 6.0 of 10

    COSMOS predicts the performance and cost of QLoRA fine-tuning and retrieval-augmented in-context learning across LLMs, achieving 1.09% mean absolute error and 92.72% average cost reduction on eight benchmarks.

  2. LLM-AutoDiff: Auto-Differentiate Any LLM Workflow

    cs.CL 2025-01 conditional novelty 5.0 of 10

    An automatic differentiation-style framework optimizes prompts across multi-component and cyclic LLM workflows, outperforming single-node textual-gradient baselines on several small benchmarks.

  3. Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models

    cs.SE 2025-07 conditional novelty 4.0 of 10

    A dual-retrieval, threshold-gated, full-parameter fine-tuned code LLM (SelRepair) reports state-of-the-art exact-match patch generation on Tufano and VulRepair benchmarks.

  4. Evaluating Hybrid Retrieval Augmented Generation using Dynamic Test Sets: LiveRAG Challenge

    cs.CL 2025-06 conditional novelty 3.0 of 10

    A hybrid BM25-plus-dense RAG system finished 4th in faithfulness and 11th in correctness at LiveRAG 2025, and its analysis found vocabulary alignment between questions and documents to be the most important performanc...

Pith tools