Pith. sign in

REVIEW 13 cited by

Tuning Language Models by Proxy

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 2401.08565 v4 pith:7TPGR7V4 submitted 2024-01-16 cs.CL

classification cs.CL
keywords tuningadaptationmodelspredictionsproxy-tuningwhenachieveblack-box
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Despite the general capabilities of large pretrained language models, they consistently benefit from further adaptation to better achieve desired behaviors. However, tuning these models has become increasingly resource-intensive, or impossible when model weights are private. We introduce proxy-tuning, a lightweight decoding-time algorithm that operates on top of black-box LMs to achieve the same end as direct tuning, but by accessing only its predictions over the output vocabulary, not its parameters. Our method tunes a smaller LM, then applies the difference between the predictions of the small tuned and untuned LMs to shift the original predictions of the larger untuned model in the direction of tuning, while retaining the benefits of larger-scale pretraining. In experiments, when we apply proxy-tuning to Llama2-70B using proxies of only 7B size, we can close 88% of the gap between Llama2-70B and its truly-tuned chat version, when evaluated across knowledge, reasoning, and safety benchmarks. We then demonstrate the generality of proxy-tuning by applying it to domain adaptation on code, and task-specific finetuning on question-answering and math problems. Finally, we show how to proxy-tune a truly black-box LM, GPT-3.5, for temporal adaptation, increasing its knowledge about recent events. Our work demonstrates the promise of using small tuned LMs to efficiently customize large, potentially proprietary LMs through decoding-time guidance.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 13 Pith papers

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

  1. Weak-to-Strong Generalization via Direct On-Policy Distillation

    cs.LG 2026-07 conditional novelty 7.0 of 10

    Transferring the log-ratio of a small model's pre-RL and post-RL checkpoints provides a dense implicit reward that improves stronger student models at a fraction of the cost of direct RL.

  2. Decoupled Contrastive Decoding via Expert-Aligned Drafting

    cs.CL 2026-08 conditional novelty 6.0 of 10

    DCD, an expert-aligned proposal path with unchanged contrastive verification, speeds up contrastive decoding by 1.65 to 1.95x on 8B models while preserving the vanilla-CD output distribution.

  3. Weak-to-Strong On-Policy Distillation

    cs.LG 2026-07 conditional novelty 6.0 of 10

    A strong LLM is improved by distilling from the logit difference of two weaker models instead of from a stronger teacher.

  4. Stream Aligner: Efficient Sentence-Level Alignment via Distribution Induction

    cs.CL 2025-01 reject novelty 6.0 of 10

    A sentence-level iterative correction method is claimed to improve large language model alignment and math reasoning, but the evidence is compromised by GPT-4 serving as both trainer and judge.

  5. Ensembling Large Language Models with Process Reward-Guided Tree Search for Better Complex Reasoning

    cs.CL 2024-12 conditional novelty 6.0 of 10

    LE-MCTS searches over reasoning steps generated by different LLMs, using a process reward model to select the best trajectory, and reports accuracy gains on math benchmarks such as MATH and MathQA.

  6. Proxy Exploration and Reusable Guidance: A Modular LLM Post-Training Paradigm via Proxy-Guided Update Signals

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Relative policy-improvement signals from a weak proxy model, after simple calibration, can be transferred to improve stronger primary LLMs without re-exploring on the primary.

  7. Logits are All We Need to Adapt Closed Models

    cs.LG 2025-02 reject novelty 5.0 of 10

    Plugin trains a small autoregressive model to multiply its softmax into a frozen LLM's softmax, adapting the output distribution to a target domain using only logits and limited data.

  8. A Survey on Training-free Alignment of Large Language Models

    cs.CL 2025-08 conditional novelty 4.0 of 10

    A survey that catalogs and categorizes training-free LLM alignment methods into pre-decoding, in-decoding, and post-decoding, with a limited experimental comparison on one model.

  9. Logit Arithmetic Elicits Long Reasoning Capabilities Without Training

    cs.CL 2025-07 conditional novelty 4.0 of 10

    ThinkLogit blends logits from a small reasoning guider into a frozen 32B model, improving math pass@1 by up to 29% without training the large model.

  10. Scalable, Symbiotic, AI and Non-AI Agent Based Parallel Discrete Event Simulations

    cs.CL 2025-05 conditional novelty 4.0 of 10

    PDES orchestration of small language models with non-AI verifier agents raises accuracy on four toy tasks from about 23 percent to 68 percent, with the verifiers supplying most of the correctness.

  11. Neural Incompatibility: The Unbridgeable Gap of Cross-Scale Parametric Knowledge Transfer in Large Language Models

    cs.CL 2025-05 conditional novelty 4.0 of 10

    Directly transferring parameters between differently-sized language models is unreliable; the paper proposes a pre-alignment method (LaTen) and explains the failure via 'Neural Incompatibility'.

  12. Towards Harnessing the Collaborative Power of Large and Small Models for Domain Tasks

    cs.LG 2025-04 conditional novelty 4.0 of 10

    The paper organizes large-small model collaboration into downward, upward, and inference-time transfer, and advocates multi-objective benchmarks for private-domain tasks.

  13. Best Practices for Large Language Models in Radiology

    cs.AI 2024-12 conditional novelty 3.0 of 10

    The paper recommends starting LLM use in radiology with prompt optimization and retrieval augmentation, fine-tuning only when needed, and preferring locally hosted open models with human expert evaluation.

Pith tools