按年被提到
20232023 · 7 次2026
AI 安全、伦理与社会影响›大模型与人类行为·arXiv:2305.00050 · cs.AI

Causal Reasoning and Large Language Models: Opening a New Frontier for Causality

Emre Kıcıman, Robert Ness, Amit Sharma, Chenhao Tan · 2023
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2023-05-02 · 最近 2023-07-11
2不同的人
2活跃月份
6讨论串
209被引(OpenAlex)
arXiv 摘要(候选层不写导读)

The causal capabilities of large language models (LLMs) are a matter of significant debate, with critical implications for the use of LLMs in societally impactful domains such as medicine, science, law, and policy. We conduct a "behavorial" study of LLMs to benchmark their capability in generating causal arguments. Across a wide range of tasks, we find that LLMs can generate text corresponding to correct causal arguments with high probability, surpassing the best-performing existing methods. Algorithms based on GPT-3.5 and 4 outperform existing algorithms on a pairwise causal discovery task (97%, 13 points gain), counterfactual reasoning task (92%, 20 points gain) and event causality (86% accuracy in determining necessary and sufficient causes in vignettes). We perform robustness checks across tasks and show that the capabilities cannot be explained by dataset memorization alone, especially since LLMs generalize to novel datasets that were created after the training cutoff date. That said, LLMs exhibit unpredictable failure modes, and we discuss the kinds of errors that may be improved and what are the fundamental limits of LLM-based answers. Overall, by operating on the text metadata, LLMs bring capabilities so far understood to be restricted to humans, such as using collected knowledge to generate causal graphs or identifying background causal context from natural language. As a result, LLMs may be used by human domain experts to save effort in setting up a causal analysis, one of the biggest impediments to the widespread adoption of causal methods. Given that LLMs ignore the actual data, our results also point to a fruitful research direction of developing algorithms that combine LLMs with existing causal techniques. Code and datasets are available at https://github.com/py-why/pywhy-llm.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论og_kalu · 2023-05

“LLMs are not very bad at reasoning. People say this but struggle to demonstrate how. There are many types of reasoning. For some like abstract analogical reasoning, LLMs are top % performers. https://arxiv.org/abs/2212.09196 There's many papers at this point demonstrating pretty strong reasoning. From Casual Reasoning, and explanatory reasoning to algo…”

LLMs are not greater than the sum of their parts: Stanford researchers原评论 ↗
评论og_kalu · 2023-05

“No world model ? A world model is so obvious papers like these are more confirmation than surprise https://arxiv.org/abs/2305.11169 https://arxiv.org/abs/2210.13382 There a certain sentiment that AGI however you wish to define it won't infact be a "We'll know it when we see it" situation but rather a "AGI will arrive long before consensus reaches its …”

Just Calm Down About GPT-4 Already原评论 ↗
评论og_kalu · 2023-05

“>It's not better at reasoning. It's barely even capable of it You are wrong. and there's many papers to show otherwise. Algorithmic, Casual, Inference, Analogical LLMs reason just fine https://arxiv.org/abs/2212.09196 https://arxiv.org/abs/2305.00050 https://arxiv.org/abs/2204.02329 https://arxiv.org/abs/2211.09066”

Governance of Superintelligence原评论 ↗
评论chaxor · 2023-05

“There are substantial works already showing reasoning capabilities in GPT-4, which show that these models do reason extremely well - near human performance for many causal reasoning tasks. (1) Additionally, there is a mathematical proof that these systems align with dynamic programming, and therefore can do algorithmic reasoning. (2,3) 1) https://arxiv.o…”

It's not just statistics: GPT-4 does reason原评论 ↗
评论chaxor · 2023-05

“Perhaps, but taken with other works in the area, a better picture does emerge regarding this claim. Substantial works already showing reasoning capabilities in GPT-4, which show that these models do reason very well - near human performance for many causal reasoning tasks. (1) Additionally, there is a mathematical proof that these systems align with dyna…”

It's not just statistics: GPT-4 does reason原评论 ↗
评论og_kalu · 2023-07

“>I doubt it, but according the the article, it's reasonable to assume the LLM would be progressively worse. I genuinely don't see how that would be a reasonable assumption. >Will humans do worse in base-3 than base-9? Why not? If you haven't learnt base 3 but you have base 9 you'll do poorer on it. >That, IMO, is an indicator that something different …”

AI Safety and the Age of Dislightenment原评论 ↗
被提交为 story · 1 次