# Reasoning Elicitation in Language Models via Counterfactual Feedback

arXiv: https://arxiv.org/abs/2410.03767 · HTML: https://mlsanity.com/paper/2410.03767/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Placed in Causal reasoning in LLMs, one of 17 directions in LLM reasoning.
- Builds on 23 of its 61 references that are in the map.
- First posted on arXiv 2 Oct 2024.

## Placed in

- LLM reasoning / [Causal reasoning in LLMs](https://mlsanity.com/lr/causal-reasoning-in-llms/)

## Builds on (most cited first, 23 of 23)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone](https://mlsanity.com/paper/2404.14219/) (2024)
- [Causal Reasoning and Large Language Models: Opening a New Frontier for Causality](https://mlsanity.com/paper/2305.00050/) (2023)
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [Fine-tuning Language Models for Factuality](https://mlsanity.com/paper/2311.08401/) (2023)
- [OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset](https://mlsanity.com/paper/2402.10176/) (2024)
- [A Distributional Approach to Controlled Text Generation](https://mlsanity.com/paper/2012.11635/) (2020)
- [Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning](https://mlsanity.com/paper/2403.20046/) (2024)
- [Understanding Causality with Large Language Models: Feasibility and Opportunities](https://mlsanity.com/paper/2304.05524/) (2023)
- [FLAME: Factuality-Aware Alignment for Large Language Models](https://mlsanity.com/paper/2405.01525/) (2024)
- [CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Models](https://mlsanity.com/paper/2112.11941/) (2021)
- [LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Study](https://mlsanity.com/paper/2405.00722/) (2024)
- [Sample Efficient Text Summarization Using a Single Pre-Trained Transformer](https://mlsanity.com/paper/1905.08836/) (2019)
- [Cause and Effect: Can Large Language Models Truly Understand Causality?](https://mlsanity.com/paper/2402.18139/) (2024)
- [Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMs](https://mlsanity.com/paper/2304.11164/) (2023)
- [Large language models for aspect-based sentiment analysis](https://mlsanity.com/paper/2310.18025/) (2023)
- [Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoning](https://mlsanity.com/paper/2404.12966/) (2024)
- [Optimizing Language Models for Human Preferences is a Causal Inference Problem](https://mlsanity.com/paper/2402.14979/) (2024)
- [Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models](https://mlsanity.com/paper/2408.08210/) (2024)
- [TRIALSCOPE: A Unifying Causal Framework for Scaling Real-World Evidence Generation with Biomedical Language Models](https://mlsanity.com/paper/2311.01301/) (2023)

## Built on by (most cited first, 14 of 14)

- [Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoning](https://mlsanity.com/paper/2506.09853/) (2025)
- [RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluation](https://mlsanity.com/paper/2506.15455/) (2025)
- [Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code](https://mlsanity.com/paper/2510.01539/) (2025)
- [Compositional Causal Reasoning Evaluation in Language Models](https://mlsanity.com/paper/2503.04556/) (2025)
- [CausalARC: Abstract Reasoning with Causal World Models](https://mlsanity.com/paper/2509.03636/) (2025)
- [FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoning](https://mlsanity.com/paper/2604.10693/) (2026)
- [How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Dataset](https://mlsanity.com/paper/2511.06418/) (2025)
- [Omitted Variable Bias in Language Models Under Distribution Shift](https://mlsanity.com/paper/2602.16784/) (2026)
- [Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Models](https://mlsanity.com/paper/2507.02928/) (2025)
- [Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistency](https://mlsanity.com/paper/2602.16787/) (2026)
- [CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulators](https://mlsanity.com/paper/2605.09079/) (2026)
- [Position: Reasoning is a Learnable Rule-Based Process](https://mlsanity.com/paper/2608.12325/) (2026)
- [Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Models](https://mlsanity.com/paper/2609.23650/) (2026)
- [Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisions](https://mlsanity.com/paper/2609.39608/) (2026)

## Abstract (arXiv)

Despite the increasing effectiveness of language models, their reasoning capabilities remain underdeveloped. In particular, causal reasoning through counterfactual question answering is lacking. This work aims to bridge this gap. We first derive novel metrics that balance accuracy in factual and counterfactual questions, capturing a more complete view of the reasoning abilities of language models than traditional factual-only based metrics. Second, we propose several fine-tuning approaches that aim to elicit better reasoning mechanisms, in the sense of the proposed metrics. Finally, we evaluate the performance of the fine-tuned language models in a variety of realistic scenarios. In particular, we investigate to what extent our fine-tuning approaches systemically achieve better generalization with respect to the base models in several problems that require, among others, inductive and deductive reasoning capabilities.