Pith. sign in

REVIEW 7 cited by

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

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 2301.11916 v4 pith:NWLC5F2S submitted 2023-01-27 cs.CL cs.AIcs.LG

classification cs.CLcs.AIcs.LG
keywords modelsdemonstrationslearningllmsreal-worldcapabilityin-contextlanguage
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In recent years, pre-trained large language models (LLMs) have demonstrated remarkable efficiency in achieving an inference-time few-shot learning capability known as in-context learning. However, existing literature has highlighted the sensitivity of this capability to the selection of few-shot demonstrations. Current understandings of the underlying mechanisms by which this capability arises from regular language model pretraining objectives remain disconnected from the real-world LLMs. This study aims to examine the in-context learning phenomenon through a Bayesian lens, viewing real-world LLMs as latent variable models. On this premise, we propose an algorithm to select optimal demonstrations from a set of annotated data with a small LM, and then directly generalize the selected demonstrations to larger LMs. We demonstrate significant improvement over baselines, averaged over eight GPT models on eight real-world text classification datasets. We also demonstrate the real-world usefulness of our algorithm on GSM8K, a math word problem dataset. Our empirical findings support our hypothesis that LLMs implicitly infer a latent variable containing task information.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

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

  1. Adaptive Task Vectors for Large Language Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    Adaptive Task Vectors use a small model to generate query-specific steering vectors for frozen LLMs, reporting strong accuracy and generalization, though the theoretical equivalences to LoRA and Prefix-Tuning are not ...

  2. Transformers as Multi-task Learners: Decoupling Features in Hidden Markov Models

    cs.LG 2025-06 conditional novelty 6.0 of 10

    A hand-constructed O(ln L + T)-layer Transformer is shown to approximate low-rank hidden Markov models in-context, with lower layers extracting local history features and upper layers performing regression-based decoding.

  3. The Role of Diversity in In-Context Learning for Large Language Models

    cs.CL 2025-05 conditional novelty 6.0 of 10

    Diversity-aware selection of in-context examples improves performance on complex and out-of-distribution tasks, though effect sizes are often modest.

  4. Scaling sparse feature circuit finding for in-context learning

    cs.LG 2025-04 conditional novelty 6.0 of 10

    Task vectors for in-context learning decompose into sparse SAE features that detect and execute tasks, linked by an attention/MLP circuit in Gemma-1 2B.

  5. SketchFlex: Facilitating Spatial-Semantic Coherence in Text-to-Image Generation with Region-Based Sketches

    cs.HC 2025-02 conditional novelty 6.0 of 10

    SketchFlex combines sketch-aware prompt recommendation with decompose-and-recompose shape refinement to help novices generate multi-object images from rough region sketches.

  6. DICE: Dynamic In-Context Example Selection in LLM Agents via Efficient Knowledge Transfer

    cs.AI 2025-07 conditional novelty 5.0 of 10

    DICE dynamically retrieves the most relevant in-context demonstrations at each agent step, and in this preprint it raises exact-match and success-rate scores on HotpotQA, ALFWorld, and Webshop across ReAct, Reflexion,...

  7. Towards Contamination Resistant Benchmarks

    cs.CL 2025-05 conditional novelty 4.0 of 10

    The authors define contamination resistance as a benchmark property and show that most tested LLMs score near zero on Caesar-cipher encoding and decoding when the shift is not 3 and the text is random nonsense.

Pith tools