Pith. sign in

REVIEW 1 cited by

Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning

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 2311.09712 v1 pith:A6UUCIHP submitted 2023-11-16 cs.CL

Regularized Conventions: Equilibrium Computation as a Model of Pragmatic Reasoning

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

We present a model of pragmatic language understanding, where utterances are produced and understood by searching for regularized equilibria of signaling games. In this model (which we call ReCo, for Regularized Conventions), speakers and listeners search for contextually appropriate utterance--meaning mappings that are both close to game-theoretically optimal conventions and close to a shared, ''default'' semantics. By characterizing pragmatic communication as equilibrium search, we obtain principled sampling algorithms and formal guarantees about the trade-off between communicative success and naturalness. Across several datasets capturing real and idealized human judgments about pragmatic implicatures, ReCo matches or improves upon predictions made by best response and rational speech act models of language understanding.

discussion (0)

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

Forward citations

Cited by 1 Pith paper

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

  1. Provably Optimal Learning Algorithms for Assistance Games

    cs.LG 2026-07 accept novelty 7.5

    Decentralized poly-time algorithms achieve (1-1/e)-approximate assistance regret Õ(T^{3/4}) (or Õ(√T) with shared randomness) for online assistance games, and better approximation is intractable.