English
Related papers

Related papers: Alignment midtraining for animals

200 papers

This paper looks at philosophical questions that arise in the context of AI alignment. It defends three propositions. First, normative and technical aspects of the AI alignment problem are interrelated, creating space for productive…

Computers and Society · Computer Science 2020-10-07 Iason Gabriel

The recent rise in popularity of large language models (LLMs) has prompted considerable concerns about their moral capabilities. Although considerable effort has been dedicated to aligning LLMs with human moral values, existing benchmarks…

Artificial Intelligence · Computer Science 2025-08-19 Alessio Galatolo , Luca Alberto Rappuoli , Katie Winkle , Meriem Beloucif

The quality of finetuning data is crucial for aligning large language models (LLMs) with human values. Current methods to improve data quality are either labor-intensive or prone to factual errors caused by LLM hallucinations. This paper…

Computation and Language · Computer Science 2024-04-18 Run-Ze Fan , Xuefeng Li , Haoyang Zou , Junlong Li , Shwai He , Ethan Chern , Jiewen Hu , Pengfei Liu

Identifying human morals and values embedded in language is essential to empirical studies of communication. However, researchers often face substantial difficulty navigating the diversity of theoretical frameworks and data available for…

Computation and Language · Computer Science 2025-09-30 Ziyu Chen , Junfei Sun , Chenxi Li , Tuan Dung Nguyen , Jing Yao , Xiaoyuan Yi , Xing Xie , Chenhao Tan , Lexing Xie

Multi-modal large language models (MLLMs) are expected to support multi-turn queries of interchanging image and text modalities in production. However, the current MLLMs trained with visual-question-answering (VQA) datasets could suffer…

Computation and Language · Computer Science 2024-11-06 Shengzhi Li , Rongyu Lin , Shichao Pei

Although humans inherently have diverse values, current large language model (LLM) alignment methods often assume that aligning LLMs with the general public's preferences is optimal. A major challenge in adopting a more individualized…

Computation and Language · Computer Science 2024-11-06 Seongyun Lee , Sue Hyun Park , Seungone Kim , Minjoon Seo

Adapting large language models (LLMs) to specialized financial reasoning typically requires expensive fine-tuning that produces model-locked expertise. Training-free alternatives have emerged, yet our experiments show that leading methods…

Computation and Language · Computer Science 2026-03-18 Tik Yu Yim , Wenting Tan , Sum Yee Chan , Tak-Wah Lam , Siu Ming Yiu

The purpose of instruction tuning is enabling zero-shot performance, but instruction tuning has also been shown to improve chain-of-thought reasoning and value alignment (Si et al., 2023). Here we consider the impact on…

Computation and Language · Computer Science 2024-10-04 Constanza Fierro , Jiaang Li , Anders Søgaard

Organizations are increasingly adopting and adapting Large Language Models (LLMs) hosted on public repositories such as HuggingFace. Although these adaptations often improve performance on specialized downstream tasks, recent evidence…

Artificial Intelligence · Computer Science 2025-11-04 Mina Taraghi , Yann Pequignot , Amin Nikanjam , Mohamed Amine Merzouk , Foutse Khomh

We consider the problem of fitting a reinforcement learning (RL) model to some given behavioral data under a multi-armed bandit environment. These models have received much attention in recent years for characterizing human and animal…

Computational Engineering, Finance, and Science · Computer Science 2026-03-27 Hao Zhu , Jasper Hoffmann , Baohe Zhang , Joschka Boedecker

Large language models are increasingly influencing human moral decisions, yet current approaches focus primarily on evaluating rather than actively steering their moral decisions. We formulate this as an out-of-distribution moral alignment…

Artificial Intelligence · Computer Science 2025-11-18 Zhiyu An , Wan Du

There is an emerging consensus that we need to align AI systems with human values (Gabriel, 2020; Ji et al., 2024), but it remains unclear how to apply this to language models in practice. We split the problem of "aligning to human values"…

Computers and Society · Computer Science 2024-04-18 Oliver Klingefjord , Ryan Lowe , Joe Edelman

The goal of vision-language modeling is to allow models to tie language understanding with visual inputs. The aim of this paper is to evaluate and align the Visual Language Model (VLM) called Multimodal Augmentation of Generative Models…

Computer Vision and Pattern Recognition · Computer Science 2022-10-26 Jean-Charles Layoun , Alexis Roger , Irina Rish

Recent AI agents, such as ChatGPT and LLaMA, primarily rely on instruction tuning and reinforcement learning to calibrate the output of large language models (LLMs) with human intentions, ensuring the outputs are harmless and helpful.…

Computation and Language · Computer Science 2025-02-14 Jingxin Xu , Guoshun Nan , Sheng Guan , Sicong Leng , Yilian Liu , Zixiao Wang , Yuyang Ma , Zhili Zhou , Yanzhao Hou , Xiaofeng Tao

Recently, the instruction-tuning of large language models is a crucial area of research in the field of natural language processing. Due to resource and cost limitations, several researchers have employed parameter-efficient tuning…

Computation and Language · Computer Science 2023-04-19 Xianghui Sun , Yunjie Ji , Baochang Ma , Xiangang Li

Instruct models, obtained from various instruction tuning or post-training steps, are commonly deemed superior and more usable than their base counterpart. While the model gains instruction following ability, instruction tuning may lead to…

Computation and Language · Computer Science 2025-09-23 Ozan İrsoy , Pengxiang Cheng , Jennifer L. Chen , Daniel Preoţiuc-Pietro , Shiyue Zhang , Duccio Pappadopulo

Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans. Traditional approaches to value alignment use imitation learning or preference learning to infer…

Artificial Intelligence · Computer Science 2019-12-10 Spencer Frazier , Md Sultan Al Nahian , Mark Riedl , Brent Harrison

Human annotators typically provide annotated data for training machine learning models, such as neural networks. Yet, human annotations are subject to noise, impairing generalization performances. Methodological research on approaches…

Computer Vision and Pattern Recognition · Computer Science 2024-07-31 Marek Herde , Denis Huseljic , Lukas Rauch , Bernhard Sick

Pretraining large language models is a complex endeavor influenced by multiple factors, including model architecture, data quality, training continuity, and hardware constraints. In this paper, we share insights gained from the experience…

Computation and Language · Computer Science 2025-04-08 Miles Q. Li , Benjamin C. M. Fung , Shih-Chia Huang

Argument mining is a subfield of argumentation that aims to automatically extract argumentative structures and their relations from natural language texts. This paper investigates how a single large language model can be leveraged to…

Computation and Language · Computer Science 2025-08-26 Henri Savigny , Bruno Yun