From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models

• URL: http://arxiv.org/abs/2308.12014v2
• Date: Mon, 4 Sep 2023 03:32:05 GMT
• Title: From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models
• Authors: Jing Yao, Xiaoyuan Yi, Xiting Wang, Jindong Wang and Xing Xie
• Abstract summary: We conduct a survey of different alignment goals in existing work and trace their evolution paths to help identify the most essential goal. Our analysis reveals a goal transformation from fundamental abilities to value orientation, indicating the potential of intrinsic human values as the alignment goal for enhanced LLMs.
• Score: 48.326660953180145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Big models, exemplified by Large Language Models (LLMs), are models typically pre-trained on massive data and comprised of enormous parameters, which not only obtain significantly improved performance across diverse tasks but also present emergent capabilities absent in smaller models. However, the growing intertwining of big models with everyday human lives poses potential risks and might cause serious social harm. Therefore, many efforts have been made to align LLMs with humans to make them better follow user instructions and satisfy human preferences. Nevertheless, `what to align with' has not been fully discussed, and inappropriate alignment goals might even backfire. In this paper, we conduct a comprehensive survey of different alignment goals in existing work and trace their evolution paths to help identify the most essential goal. Particularly, we investigate related works from two perspectives: the definition of alignment goals and alignment evaluation. Our analysis encompasses three distinct levels of alignment goals and reveals a goal transformation from fundamental abilities to value orientation, indicating the potential of intrinsic human values as the alignment goal for enhanced LLMs. Based on such results, we further discuss the challenges of achieving such intrinsic value alignment and provide a collection of available resources for future research on the alignment of big models.

Related papers

• Adversarial Alignment for LLMs Requires Simpler, Reproducible, and More Measurable Objectives [52.863024096759816]
  Misaligned research objectives have hindered progress in adversarial robustness research over the past decade. We argue that realigned objectives are necessary for meaningful progress in adversarial alignment.
  arXiv  Detail & Related papers  (2025-02-17T15:28:40Z)
• Evaluating the Paperclip Maximizer: Are RL-Based Language Models More Likely to Pursue Instrumental Goals? [33.11148546999906]
  Key concern is textitinstrumental convergence, where an AI system develops unintended intermediate goals that override the ultimate objective and deviate from human-intended goals. This issue is particularly relevant in reinforcement learning (RL)-trained models, which can generate creative but unintended strategies to maximize rewards. We show that RL-driven models exhibit a stronger tendency for instrumental convergence due to their optimization of goal-directed behavior in ways that may misalign with human intentions.
  arXiv  Detail & Related papers  (2025-02-16T16:29:20Z)
• The Superalignment of Superhuman Intelligence with Large Language Models [63.96120398355404]
  We discuss the concept of superalignment from the learning perspective to answer this question. We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation. We present a conceptual framework for superalignment, which consists of three modules: an attacker which generates adversary queries trying to expose the weaknesses of a learner model; a learner which will refine itself by learning from scalable feedbacks generated by a critic model along with minimal human experts; and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing.
  arXiv  Detail & Related papers  (2024-12-15T10:34:06Z)
• Rethinking Multi-Objective Learning through Goal-Conditioned Supervised Learning [8.593384839118658]
  Multi-objective learning aims to optimize multiple objectives simultaneously with a single model. It suffers from the difficulty to formalize and conduct the exact learning process. We propose a general framework for automatically learning to achieve multiple objectives based on the existing sequential data.
  arXiv  Detail & Related papers  (2024-12-12T03:47:40Z)
• On the Modeling Capabilities of Large Language Models for Sequential Decision Making [52.128546842746246]
  Large pretrained models are showing increasingly better performance in reasoning and planning tasks. We evaluate their ability to produce decision-making policies, either directly, by generating actions, or indirectly. In environments with unfamiliar dynamics, we explore how fine-tuning LLMs with synthetic data can significantly improve their reward modeling capabilities.
  arXiv  Detail & Related papers  (2024-10-08T03:12:57Z)
• Seeing Eye to AI: Human Alignment via Gaze-Based Response Rewards for Large Language Models [46.09562860220433]
  We introduce GazeReward, a novel framework that integrates implicit feedback -- and specifically eye-tracking (ET) data -- into the Reward Model (RM) Our approach significantly improves the accuracy of the RM on established human preference datasets.
  arXiv  Detail & Related papers  (2024-10-02T13:24:56Z)
• Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment [103.12563033438715]
  Alignment in artificial intelligence pursues consistency between model responses and human preferences as well as values. Existing alignment techniques are mostly unidirectional, leading to suboptimal trade-offs and poor flexibility over various objectives. We introduce controllable preference optimization (CPO), which explicitly specifies preference scores for different objectives.
  arXiv  Detail & Related papers  (2024-02-29T12:12:30Z)
• Goal-Aware Prediction: Learning to Model What Matters [105.43098326577434]
  One of the fundamental challenges in using a learned forward dynamics model is the mismatch between the objective of the learned model and that of the downstream planner or policy. We propose to direct prediction towards task relevant information, enabling the model to be aware of the current task and encouraging it to only model relevant quantities of the state space. We find that our method more effectively models the relevant parts of the scene conditioned on the goal, and as a result outperforms standard task-agnostic dynamics models and model-free reinforcement learning.
  arXiv  Detail & Related papers  (2020-07-14T16:42:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.