Zero-shot Causal Graph Extrapolation from Text via LLMs

• URL: http://arxiv.org/abs/2312.14670v1
• Date: Fri, 22 Dec 2023 13:14:38 GMT
• Title: Zero-shot Causal Graph Extrapolation from Text via LLMs
• Authors: Alessandro Antonucci, Gregorio Piqu\'e, Marco Zaffalon
• Abstract summary: We evaluate the ability of large language models (LLMs) to infer causal relations from natural language. LLMs show competitive performance in a benchmark of pairwise relations without needing (explicit) training samples. We extend our approach to extrapolating causal graphs through iterated pairwise queries.
• Score: 50.596179963913045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We evaluate the ability of large language models (LLMs) to infer causal relations from natural language. Compared to traditional natural language processing and deep learning techniques, LLMs show competitive performance in a benchmark of pairwise relations without needing (explicit) training samples. This motivates us to extend our approach to extrapolating causal graphs through iterated pairwise queries. We perform a preliminary analysis on a benchmark of biomedical abstracts with ground-truth causal graphs validated by experts. The results are promising and support the adoption of LLMs for such a crucial step in causal inference, especially in medical domains, where the amount of scientific text to analyse might be huge, and the causal statements are often implicit.

Related papers

• JustLogic: A Comprehensive Benchmark for Evaluating Deductive Reasoning in Large Language Models [51.99046112135311]
  We introduce JustLogic, a synthetically generated deductive reasoning benchmark for rigorous evaluation of Large Language Models. JustLogic is highly complex, capable of generating a diverse range of linguistic patterns, vocabulary, and argument structures. Our experimental results reveal that most state-of-the-art (SOTA) LLMs perform significantly worse than the human average.
  arXiv  Detail & Related papers  (2025-01-24T15:49:10Z)
• Argumentation Computation with Large Language Models : A Benchmark Study [6.0682923348298194]
  Large language models (LLMs) have made significant advancements in neuro-symbolic computing. We aim to investigate the capability of LLMs in determining the extensions of various abstract argumentation semantics.
  arXiv  Detail & Related papers  (2024-12-21T18:23:06Z)
• Counterfactual Causal Inference in Natural Language with Large Language Models [9.153187514369849]
  We propose an end-to-end causal structure discovery and causal inference method from natural language. We first use an LLM to extract the instantiated causal variables from text data and build a causal graph. We then conduct counterfactual inference on the estimated graph.
  arXiv  Detail & Related papers  (2024-10-08T21:53:07Z)
• Enhancing Logical Reasoning in Large Language Models through Graph-based Synthetic Data [53.433309883370974]
  This work explores the potential and limitations of using graph-based synthetic reasoning data as training signals to enhance Large Language Models' reasoning capabilities. Our experiments, conducted on two established natural language reasoning tasks, demonstrate that supervised fine-tuning with synthetic graph-based reasoning data effectively enhances LLMs' reasoning performance without compromising their effectiveness on other standard evaluation benchmarks.
  arXiv  Detail & Related papers  (2024-09-19T03:39:09Z)
• Prompt-based vs. Fine-tuned LLMs Toward Causal Graph Verification [0.0]
  This work aims toward an application of natural language processing (NLP) technology for automatic verification of causal graphs using text sources. We compare the performance of two types of NLP models: (1) pre-trained language models fine-tuned for causal relation classification task and, (2) prompt-based LLMs.
  arXiv  Detail & Related papers  (2024-05-29T09:06:18Z)
• The Emergence of Large Language Models in Static Analysis: A First Look through Micro-Benchmarks [3.848607479075651]
  We investigate the role that current Large Language Models (LLMs) can play in improving callgraph analysis and type inference for Python programs. Our study reveals that LLMs show promising results in type inference, demonstrating higher accuracy than traditional methods, yet they exhibit limitations in callgraph analysis.
  arXiv  Detail & Related papers  (2024-02-27T16:53:53Z)
• Causal Inference Using LLM-Guided Discovery [34.040996887499425]
  We show that the topological order over graph variables (causal order) alone suffices for causal effect inference. We propose a robust technique of obtaining causal order from Large Language Models (LLMs) Our approach significantly improves causal ordering accuracy as compared to discovery algorithms.
  arXiv  Detail & Related papers  (2023-10-23T17:23:56Z)
• Interpretable Medical Diagnostics with Structured Data Extraction by Large Language Models [59.89454513692417]
  Tabular data is often hidden in text, particularly in medical diagnostic reports. We propose a novel, simple, and effective methodology for extracting structured tabular data from textual medical reports, called TEMED-LLM. We demonstrate that our approach significantly outperforms state-of-the-art text classification models in medical diagnostics.
  arXiv  Detail & Related papers  (2023-06-08T09:12:28Z)
• Can large language models build causal graphs? [54.74910640970968]
  Large language models (LLMs) represent an opportunity to ease the process of building causal graphs. LLMs have been shown to be brittle to the choice of probing words, context, and prompts that the user employs.
  arXiv  Detail & Related papers  (2023-03-07T22:05:31Z)
• Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge [59.22170796793179]
  Transformers Language Models (TLMs) were tested on a benchmark for the textitdynamic estimation of thematic fit Our results show that TLMs can reach performances that are comparable to those achieved by SDM. However, additional analysis consistently suggests that TLMs do not capture important aspects of event knowledge.
  arXiv  Detail & Related papers  (2021-07-22T20:52:26Z)

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.