paper-with-me

홈 › Papers

Reverse-Engineering the Reader

2024-10-16 · Samuel Kiegeland, Ethan Gotlieb Wilcox, Afra Amini, David Robert Reich, Ryan Cotterell

Numerous previous studies have sought to determine to what extent language models, pretrained on natural language text, can serve as useful models of human cognition. In this paper, we are interested in the opposite question: whether we can directly optimize a language model to be a useful cognitive model by aligning it to human psychometric data. To achieve this, we introduce a novel alignment technique in which we fine-tune a language model to implicitly optimize the parameters of a linear regressor that directly predicts humans' reading times of in-context linguistic units, e.g., phonemes, morphemes, or words, using surprisal estimates derived from the language model. Using words as a test case, we evaluate our technique across multiple model sizes and datasets and find that it improves language models' psychometric predictive power. However, we find an inverse relationship between psychometric power and a model's performance on downstream NLP tasks as well as its perplexity on held-out test data. While this latter trend has been observed before (Oh et al., 2022; Shain et al., 2024), we are the first to induce it by manipulating a model's alignment to psychometric data.

📄 PDF Abstract BibTeX arXiv:2410.13086

Code (1)

samuki/reverse-engineering-the-reader 공식 구현 pytorch

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

LSP Framework: A Compensatory Model for Defeating Trigger Reverse Engineering via Label Smoothing Poisoning

2024-04-19 · Beichen Li, Yuanfang Guo, Heqi Peng, Yangxi Li 외

Deep neural networks are vulnerable to backdoor attacks. Among the existing backdoor defense methods, trigger reverse engineering based approaches, which reconstruct the backdoor triggers via optimizations, are the most …

Backdoor Attackbackdoor defense

Multi-modal Learning for WebAssembly Reverse Engineering

2024-04-04 · Hanxian Huang, Jishen Zhao

The increasing adoption of WebAssembly (Wasm) for performance-critical and security-sensitive tasks drives the demand for WebAssembly program comprehension and reverse engineering. Recent studies have introduced machine …

Language ModellingSelf-Supervised Learning

Hardware Trust and Assurance through Reverse Engineering: A Survey and Outlook from Image Analysis and Machine Learning Perspectives

2020-02-11 · Ulbert J. Botero, Ronald Wilson, Hangwei Lu, Mir Tanjidur Rahman 외

In the context of hardware trust and assurance, reverse engineering has been often considered as an illegal action. Generally speaking, reverse engineering aims to retrieve information from a product, i.e., integrated ci…

Rethinking the Reverse-engineering of Trojan Triggers

2022-10-27 · Zhenting Wang, Kai Mei, Hailun Ding, Juan Zhai 외

Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-engineering methods only consider input spa…

Reverse-engineering Bar Charts Using Neural Networks

2020-09-05 · Fangfang Zhou, Yong Zhao, Wenjiang Chen, Yijing Tan 외

Reverse-engineering bar charts extracts textual and numeric information from the visual representations of bar charts to support application scenarios that require the underlying information. In this paper, we propose a …

Decoderobject-detectionObject Detection