Bridging Today and the Future of Humanity: AI Safety in 2024 and Beyond
Not on the map. Why?
Abstract (arXiv)
The advancements in generative AI inevitably raise concerns about their risks and safety implications, which, in return, catalyzes significant progress in AI safety. However, as this field continues to evolve, a critical question arises: are our current efforts on AI safety aligned with the advancements of AI as well as the long-term goal of human civilization? This paper presents a blueprint for an advanced human society and leverages this vision to guide current AI safety efforts. It outlines a future where the Internet of Everything becomes reality, and creates a roadmap of significant technological advancements towards this envisioned future. For each stage of the advancements, this paper forecasts potential AI safety issues that humanity may face. By projecting current efforts against this blueprint, this paper examines the alignment between the current efforts and the long-term needs, and highlights unique challenges and missions that demand increasing attention from AI safety practitioners in the 2020s. This vision paper aims to offer a broader perspective on AI safety, emphasizing that our current efforts should not only address immediate concerns but also anticipate potential risks in the expanding AI landscape, thereby promoting a safe and sustainable future of AI and human civilization.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 207 of its 370 references that are in the map. First posted on arXiv 9 Oct 2024.
Builds on
207 of 370 references.
References · 207
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 13,028
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2015Rethinking the Inception Architecture for Computer Visioncited by 5,475
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
- 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
- 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
- 2023Mistral 7Bcited by 3,164
- 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 3,104
38 more
- 2021TruthfulQA: Measuring How Models Mimic Human Falsehoodscited by 2,975
- 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,955
- 2016Deep Learning with Differential Privacycited by 2,728
- 2023A Survey of Large Language Modelscited by 2,576
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
- 2020Extracting Training Data from Large Language Modelscited by 2,189
- 2024Qwen2 Technical Reportcited by 2,120
- 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
- 2023Jailbroken: How Does LLM Safety Training Fail?cited by 1,651
- 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,601
- 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
- 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,443
- 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,429
- 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,420
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
- 2018FEVER: a large-scale dataset for Fact Extraction and VERificationcited by 1,375
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2023Representation Engineering: A Top-Down Approach to AI Transparencycited by 1,336
- 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
- 2018Don't Give Me the Details, Just the Summary! Topic-Aware Convolutional Neural Networks for Extreme Summarizationcited by 1,317
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
- 2020RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Modelscited by 1,255
- 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
- 2018Sanity Checks for Saliency Mapscited by 1,156
- 2023Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!cited by 1,154
- 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
- 2021A General Language Assistant as a Laboratory for Alignmentcited by 1,055
- 2015Teaching Machines to Read and Comprehendcited by 1,049
- 2022Red Teaming Language Models with Language Modelscited by 1,026
- 2019Deep Leakage from Gradientscited by 1,021
- 2020Beyond Accuracy: Behavioral Testing of NLP models with CheckListcited by 1,006
- 2023BloombergGPT: A Large Language Model for Financecited by 939
- 2020StereoSet: Measuring stereotypical bias in pretrained language modelscited by 924
- 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 886
- 2017RACE: Large-scale ReAding Comprehension Dataset From Examinationscited by 861
- 2023BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Datasetcited by 860
- 2022Discovering Language Model Behaviors with Model-Written Evaluationscited by 836
50 most cited of 207 All 207 (JSON)
Built on by
Citing papers per year: 2024: 1.
1 paper.