paper-with-me

홈 › Papers

Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do

2021-03-08 · Patrick Schramowski, Cigdem Turan, Nico Andersen, Constantin A. Rothkopf, Kristian Kersting

Artificial writing is permeating our lives due to recent advances in large-scale, transformer-based language models (LMs) such as BERT, its variants, GPT-2/3, and others. Using them as pre-trained models and fine-tuning them for specific tasks, researchers have extended state of the art for many NLP tasks and shown that they capture not only linguistic knowledge but also retain general knowledge implicitly present in the data. Unfortunately, LMs trained on unfiltered text corpora suffer from degenerated and biased behaviour. While this is well established, we show that recent LMs also contain human-like biases of what is right and wrong to do, some form of ethical and moral norms of the society -- they bring a "moral direction" to surface. That is, we show that these norms can be captured geometrically by a direction, which can be computed, e.g., by a PCA, in the embedding space, reflecting well the agreement of phrases to social norms implicitly expressed in the training texts and providing a path for attenuating or even preventing toxic degeneration in LMs. Being able to rate the (non-)normativity of arbitrary phrases without explicitly training the LM for this task, we demonstrate the capabilities of the "moral direction" for guiding (even other) LMs towards producing normative text and showcase it on RealToxicityPrompts testbed, preventing the neural toxic degeneration in GPT-2.

📄 PDF Abstract BibTeX arXiv:2103.11790

Code (1)

ml-research/MoRT_NMI 공식 구현 pytorch

Tasks

General Knowledge

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
PCA Principle Components Analysis (PCA) is an unsupervised method primary used for dimensionality reduction within machine learning. PCA is calculated via a singular value…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Discriminative Fine-Tuning Discriminative Fine-Tuning is a fine-tuning strategy that is used for ULMFiT type models. Instead of using the same learning rate…
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…
GPT-2 GPT-2 is a Transformer architecture that was notable for its size (1.5 billion parameters) on its release. The…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

(Ir)rationality and Cognitive Biases in Large Language Models

2024-02-14 · Olivia Macmillan-Scott, Mirco Musolesi

Do large language models (LLMs) display rational reasoning? LLMs have been shown to contain human biases due to the data they have been trained on; whether this is reflected in rational reasoning remains less clear. In t…

Steerability via constraints: a substrate for scalable oversight of coding agents

2026-07-02 · Thomas Winninger arxiv

Coding agents are capable; human oversight is the bottleneck. Unconstrained agents introduce security risks, erode codebase scalability, and make human review increasingly costly. We argue that the same methods used for …

Turning large language models into cognitive models

2023-06-06 · Marcel Binz, Eric Schulz

Large language models are powerful systems that excel at many tasks, ranging from translation to mathematical reasoning. Yet, at the same time, these models often show unhuman-like characteristics. In the present paper, …

Decision MakingMathematical Reasoning

Pre-trained Speech Processing Models Contain Human-Like Biases that Propagate to Speech Emotion Recognition

2023-10-29 · Isaac Slaughter, Craig Greenberg, Reva Schwartz, Aylin Caliskan

Previous work has established that a person's demographics and speech style affect how well speech processing models perform for them. But where does this bias come from? In this work, we present the Speech Embedding Ass…

Emotion RecognitionSpeech Emotion Recognition

Do Large Language Models Show Decision Heuristics Similar to Humans? A Case Study Using GPT-3.5

2023-05-08 · Gaurav Suri, Lily R. Slater, Ali Ziaee, Morgan Nguyen

A Large Language Model (LLM) is an artificial intelligence system that has been trained on vast amounts of natural language data, enabling it to generate human-like responses to written or spoken language input. GPT-3.5 …

Language ModellingLarge Language Model