Pith. sign in

REVIEW 4 cited by

Meta-learning via Language Model In-context Tuning

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 2110.07814 v2 pith:D4EACK7S submitted 2021-10-15 cs.CL cs.LG

Meta-learning via Language Model In-context Tuning

classification cs.CL cs.LG
keywords in-contextmodelexamplestuningbinaryclfsinputlearnabsolute
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

The goal of meta-learning is to learn to adapt to a new task with only a few labeled examples. To tackle this problem in NLP, we propose $\textit{in-context tuning}$, which recasts adaptation and prediction as a simple sequence prediction problem: to form the input sequence, we concatenate the task instruction, the labeled examples, and the target input to predict; to meta-train the model to learn from in-context examples, we fine-tune a pre-trained language model (LM) to predict the target label from the input sequences on a collection of tasks. We benchmark our method on two collections of text classification tasks: LAMA and BinaryClfs. Compared to first-order MAML which adapts the model with gradient descent, our method better leverages the inductive bias of LMs to perform pattern matching, and outperforms MAML by an absolute $6\%$ AUC ROC score on BinaryClfs, with increasing advantage w.r.t. model size. Compared to non-fine-tuned in-context learning (i.e. prompting a raw LM), in-context tuning directly learns to learn from in-context examples. On BinaryClfs, in-context tuning improves the average AUC-ROC score by an absolute $10\%$, and reduces the variance with respect to example ordering by 6x and example choices by 2x.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

    cs.CL 2022-02 accept novelty 8.0

    Randomly replacing labels in in-context demonstrations barely hurts performance, showing that label space, input distribution, and sequence format drive in-context learning more than ground-truth labels.

  2. STaR-Quant: State-Time Consistent Post-Training Quantization for Diffusion Large Language Models

    cs.LG 2026-06 unverdicted novelty 6.0

    STaR-Quant provides a state-time consistent PTQ framework for DLLMs using SGAT and TAC to improve low-bit weight-activation quantization.

  3. Binomial Gradient-Based Meta-Learning for Enhanced Meta-Gradient Estimation

    cs.LG 2026-04 unverdicted novelty 6.0

    BinomMAML uses a binomial expansion to estimate meta-gradients more accurately than prior approximations, with error bounds that improve on existing methods and decay super-exponentially under mild conditions.

  4. Fact4ac at the Financial Misinformation Detection Challenge Task: Reference-Free Financial Misinformation Detection via Fine-Tuning and Few-Shot Prompting of Large Language Models

    cs.CL 2026-04 unverdicted novelty 2.0

    LLM system with LoRA fine-tuning and few-shot prompting wins reference-free financial misinformation detection task at 95.4% public and 96.3% private accuracy.