# How is ChatGPT's behavior changing over time?

arXiv: https://arxiv.org/abs/2307.09009 · HTML: https://mlsanity.com/paper/2307.09009/

## Key facts

- Cited by 270 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 51 references that are in the map.
- First posted on arXiv 18 Jul 2023.

## Builds on (most cited first, 22 of 22)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [RealToxicityPrompts: Evaluating Neural Toxic Degeneration in Language Models](https://mlsanity.com/paper/2009.11462/) (2020)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity](https://mlsanity.com/paper/2302.04023/) (2023)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned](https://mlsanity.com/paper/2209.07858/) (2022)
- [Capabilities of GPT-4 on Medical Challenge Problems](https://mlsanity.com/paper/2303.13375/) (2023)
- [News Summarization and Evaluation in the Era of GPT-3](https://mlsanity.com/paper/2209.12356/) (2022)
- [How Language Model Hallucinations Can Snowball](https://mlsanity.com/paper/2305.13534/) (2023)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)
- [Can we trust the evaluation on ChatGPT?](https://mlsanity.com/paper/2303.12767/) (2023)
- [An Independent Evaluation of ChatGPT on Mathematical Word Problems (MWP)](https://mlsanity.com/paper/2302.13814/) (2023)
- [LMentry: A Language Model Benchmark of Elementary Language Tasks](https://mlsanity.com/paper/2211.02069/) (2022)
- [Did the Model Change? Efficiently Assessing Machine Learning API Shifts](https://mlsanity.com/paper/2107.14203/) (2021)
- [ChatLog: Carefully Evaluating the Evolution of ChatGPT Across Time](https://mlsanity.com/paper/2304.14106/) (2023)
- [HAPI: A Large-scale Longitudinal Dataset of Commercial ML API Predictions](https://mlsanity.com/paper/2209.08443/) (2022)

## Built on by (most cited first, 30 of 270)

- [Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection](https://mlsanity.com/paper/2310.11511/) (2023)
- [GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts](https://mlsanity.com/paper/2309.10253/) (2023)
- [GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher](https://mlsanity.com/paper/2308.06463/) (2023)
- [Low-Resource Languages Jailbreak GPT-4](https://mlsanity.com/paper/2310.02446/) (2023)
- [Challenges and Applications of Large Language Models](https://mlsanity.com/paper/2307.10169/) (2023)
- [Multilingual Jailbreak Challenges in Large Language Models](https://mlsanity.com/paper/2310.06474/) (2023)
- [Generative Representational Instruction Tuning](https://mlsanity.com/paper/2402.09906/) (2024)
- [Leak, Cheat, Repeat: Data Contamination and Evaluation Malpractices in Closed-Source LLMs](https://mlsanity.com/paper/2402.03927/) (2024)
- [Evaluating Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2310.19736/) (2023)
- [OctoPack: Instruction Tuning Code Large Language Models](https://mlsanity.com/paper/2308.07124/) (2023)
- [Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools](https://mlsanity.com/paper/2405.20362/) (2024)
- [Art or Artifice? Large Language Models and the False Promise of Creativity](https://mlsanity.com/paper/2309.14556/) (2023)
- [Sociotechnical Safety Evaluation of Generative AI Systems](https://mlsanity.com/paper/2310.11986/) (2023)
- [GEMBA-MQM: Detecting Translation Quality Error Spans with GPT-4](https://mlsanity.com/paper/2310.13988/) (2023)
- [Who Validates the Validators? Aligning LLM-Assisted Evaluation of LLM Outputs with Human Preferences](https://mlsanity.com/paper/2404.12272/) (2024)
- [OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset](https://mlsanity.com/paper/2402.10176/) (2024)
- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [Deception Abilities Emerged in Large Language Models](https://mlsanity.com/paper/2307.16513/) (2023)
- [Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling](https://mlsanity.com/paper/2308.06077/) (2023)
- [Where Would I Go Next? Large Language Models as Human Mobility Predictors](https://mlsanity.com/paper/2308.15197/) (2023)
- [A Systematic Survey and Critical Review on Evaluating Large Language Models: Challenges, Limitations, and Recommendations](https://mlsanity.com/paper/2407.04069/) (2024)
- [Safeguarding Large Language Models: A Survey](https://mlsanity.com/paper/2406.02622/) (2024)
- [Split and Merge: Aligning Position Biases in LLM-based Evaluators](https://mlsanity.com/paper/2310.01432/) (2023)
- [Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition](https://mlsanity.com/paper/2311.16119/) (2023)
- [Building Guardrails for Large Language Models](https://mlsanity.com/paper/2402.01822/) (2024)
- [Demonstrating specification gaming in reasoning models](https://mlsanity.com/paper/2502.13295/) (2025)
- [Self-Guard: Empower the LLM to Safeguard Itself](https://mlsanity.com/paper/2310.15851/) (2023)
- [Theory of Mind in Large Language Models: Examining Performance of 11 State-of-the-Art models vs. Children Aged 7-10 on Advanced Tests](https://mlsanity.com/paper/2310.20320/) (2023)
- [Evaluating Language Model Agency through Negotiations](https://mlsanity.com/paper/2401.04536/) (2024)
- [MEGAnno+: A Human-LLM Collaborative Annotation System](https://mlsanity.com/paper/2402.18050/) (2024)

## Abstract (arXiv)

GPT-3.5 and GPT-4 are the two most widely used large language model (LLM) services. However, when and how these models are updated over time is opaque. Here, we evaluate the March 2023 and June 2023 versions of GPT-3.5 and GPT-4 on several diverse tasks: 1) math problems, 2) sensitive/dangerous questions, 3) opinion surveys, 4) multi-hop knowledge-intensive questions, 5) generating code, 6) US Medical License tests, and 7) visual reasoning. We find that the performance and behavior of both GPT-3.5 and GPT-4 can vary greatly over time. For example, GPT-4 (March 2023) was reasonable at identifying prime vs. composite numbers (84% accuracy) but GPT-4 (June 2023) was poor on these same questions (51% accuracy). This is partly explained by a drop in GPT-4's amenity to follow chain-of-thought prompting. Interestingly, GPT-3.5 was much better in June than in March in this task. GPT-4 became less willing to answer sensitive questions and opinion survey questions in June than in March. GPT-4 performed better at multi-hop questions in June than in March, while GPT-3.5's performance dropped on this task. Both GPT-4 and GPT-3.5 had more formatting mistakes in code generation in June than in March. We provide evidence that GPT-4's ability to follow user instructions has decreased over time, which is one common factor behind the many behavior drifts. Overall, our findings show that the behavior of the "same" LLM service can change substantially in a relatively short amount of time, highlighting the need for continuous monitoring of LLMs.