Pith. sign in

REVIEW 2 cited by

Language Models are Few-Shot Butlers

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 2104.07972 v2 pith:RVF3J34J submitted 2021-04-16 cs.CL cs.LG

classification cs.CLcs.LG
keywords languagemodelsdemonstrationsenvironmentenvironmentsexpertfine-tunedsmall
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Pretrained language models demonstrate strong performance in most NLP tasks when fine-tuned on small task-specific datasets. Hence, these autoregressive models constitute ideal agents to operate in text-based environments where language understanding and generative capabilities are essential. Nonetheless, collecting expert demonstrations in such environments is a time-consuming endeavour. We introduce a two-stage procedure to learn from a small set of demonstrations and further improve by interacting with an environment. We show that language models fine-tuned with only 1.2% of the expert demonstrations and a simple reinforcement learning algorithm achieve a 51% absolute improvement in success rate over existing methods in the ALFWorld environment.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

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

  1. Embodied CoT Distillation From LLM To Off-the-shelf Agents

    cs.AI 2024-12 conditional novelty 5.0 of 10

    DeDer distills LLM chain-of-thought reasoning into a two-tier small-language-model policy (rationale writer plus planner) and reports state-of-the-art ALFRED success rates for small-model embodied agents.

  2. WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

    cs.AI 2025-04 conditional novelty 4.0 of 10

    WALL-E 2.0 improves LLM agents by encoding learned environment rules as executable code that corrects an LLM world model, lifting ALFWorld success to 98%.

Pith tools