paper-with-me

Papers

A simple repair mechanism can alleviate computational demands of pragmatic reasoning: simulations and complexity analysis

2020-11-01 · CONLL 2020 · Jacqueline van Arkel, Marieke Woensdregt, Mark Dingemanse, Mark Blokpoel

How can people communicate successfully while keeping resource costs low in the face of ambiguity? We present a principled theoretical analysis comparing two strategies for disambiguation in communication: (i) pragmatic reasoning, where communicators reason about each other, and (ii) other-initiated repair, where communicators signal and resolve trouble interactively. Using agent-based simulations and computational complexity analyses, we compare the efficiency of these strategies in terms of communicative success, computation cost and interaction cost. We show that agents with a simple repair mechanism can increase efficiency, compared to pragmatic agents, by reducing their computational burden at the cost of longer interactions. We also find that efficiency is highly contingent on the mechanism, highlighting the importance of explicit formalisation and computational rigour.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Repair 설명 없음

Similar Papers 제목 키워드 기반

NARRepair: Non-Autoregressive Code Generation Model for Automatic Program Repair

2024-06-24 · Zhenyu Yang, Zhen Yang, Zhongxing Yu

With the advancement of deep learning techniques, the performance of Automatic Program Repair(APR) techniques has reached a new level. Previous deep learning-based APR techniques essentially modified program sentences in…

Code GenerationProgram Repair

Surgical Repair of Insecure Code Generation in LLMs

2026-04-17 · Gustavo Sandoval, Brendan Dolan-Gavitt, Siddharth Garg arxiv

Large language models write production code, and yet they routinely introduce well-known vulnerabilities. We show that this is not a knowledge deficit: the same models that generate insecure code, correctly identify and …

Code Generation

Inconsistency Handling in Prioritized Databases with Universal Constraints: Complexity Analysis and Links with Active Integrity Constraints

2023-06-06 · Meghyn Bienvenu, Camille Bourgaux

This paper revisits the problem of repairing and querying inconsistent databases equipped with universal constraints. We adopt symmetric difference repairs, in which both deletions and additions of facts can be used to r…

Compute-Efficient Active Learning

2024-01-15 · NeurIPS Workshop ReALML 2023 12 · Gábor Németh, Tamás Matuszka

Active learning, a powerful paradigm in machine learning, aims at reducing labeling costs by selecting the most informative samples from an unlabeled dataset. However, the traditional active learning process often demand…

Active Learning

Even Heads Fix Odd Errors: Mechanistic Discovery and Surgical Repair in Transformer Attention

2025-08-26 · Gustavo Sandoval arxiv

We present a mechanistic case study of a format-dependent reasoning failure in Llama-3.1-8B-Instruct, where the model incorrectly judges "9.11" as larger than "9.8" in chat or Q&A formats, but answers correctly in simple…