# Context-Aware Reasoning On Parametric Knowledge for Inferring Causal Variables

arXiv: https://arxiv.org/abs/2409.02604 · HTML: https://mlsanity.com/paper/2409.02604/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 0 of its 74 references that are in the map.
- First posted on arXiv 4 Sep 2024.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)
- LLM safety and security / [Backdoor and data poisoning attacks](https://mlsanity.com/safety/backdoor-and-data-poisoning-attacks/)

## Built on by (most cited first, 6 of 6)

- [Large language models for artificial general intelligence (AGI): A survey of foundational principles and approaches](https://mlsanity.com/paper/2501.03151/) (2025)
- [CausalGraph2LLM: Evaluating LLMs for Causal Queries](https://mlsanity.com/paper/2410.15939/) (2024)
- [LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation](https://mlsanity.com/paper/2410.15828/) (2024)
- [MedG-KRP: Medical Graph Knowledge Representation Probing](https://mlsanity.com/paper/2412.10982/) (2024)
- [IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery](https://mlsanity.com/paper/2602.07943/) (2026)
- [Trustworthy AI Suffers from Invariance Conflicts and Causality is The Solution](https://mlsanity.com/paper/2605.02640/) (2026)

## Abstract (arXiv)

Scientific discovery catalyzes human intellectual advances, driven by the cycle of hypothesis generation, experimental design, evaluation, and assumption refinement. Central to this process is causal inference, uncovering the mechanisms behind observed phenomena. While randomized experiments provide strong inferences, they are often infeasible due to ethical or practical constraints. However, observational studies are prone to confounding or mediating biases. While crucial, identifying such backdoor paths is expensive and heavily depends on scientists' domain knowledge to generate hypotheses. We introduce a novel benchmark where the objective is to complete a partial causal graph. We design a benchmark with varying difficulty levels with over 4000 queries. We show the strong ability of LLMs to hypothesize the backdoor variables between a cause and its effect. Unlike simple knowledge memorization of fixed associations, our task requires the LLM to reason according to the context of the entire graph.