Pith. sign in

REVIEW 2 cited by

Iterative Decoding for Compositional Generalization in Transformers

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 2110.04169 v2 pith:D5RZTBE3 submitted 2021-10-08 cs.LG cs.CL

classification cs.LGcs.CL
keywords decodingiterativeintermediateseq2seqtransformertransformerscompositionaldatasets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i.e., to combine a set of learned primitives to solve more complex tasks. In sequence-to-sequence (seq2seq) learning, transformers are often unable to predict correct outputs for longer examples than those seen at training. This paper introduces iterative decoding, an alternative to seq2seq that (i) improves transformer compositional generalization in the PCFG and Cartesian product datasets and (ii) evidences that, in these datasets, seq2seq transformers do not learn iterations that are not unrolled. In iterative decoding, training examples are broken down into a sequence of intermediate steps that the transformer learns iteratively. At inference time, the intermediate outputs are fed back to the transformer as intermediate inputs until an end-of-iteration token is predicted. We conclude by illustrating some limitations of iterative decoding in the CFQ dataset.

Discussion (0). Sign in 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. Distance-Preserving Embeddings in Inhomogeneous Random Graphs

    cs.LG 2026-07 accept novelty 7.0 of 10

    On supercritical inhomogeneous random graphs, multi-scale landmark embeddings achieve (1±ε)-distortion of shortest paths at dimension Ω(n^{1-ε} log n), far below worst-case, with universal kernel extensions and transf...

  2. Learning neuro-symbolic convergent term rewriting systems

    cs.AI 2025-07 conditional novelty 6.0 of 10

    Two modular neuro-symbolic systems learn to simplify formulas by imitating term rewriting steps, and the new FastNRS variant generalizes to deeper formulas while being far faster than the original.

Pith tools