mlsanityData to 7 Oct 2026

Reasoning Elicitation in Language Models via Counterfactual Feedback

arXiv 2410.03767 ↗First posted 2 Oct 2024cs.CL cs.AI cs.LGcited by 14

On the map: LLM reasoning → Causal reasoning in LLMs

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.

Key facts. Cited by 14 papers in the map (data through 7 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.

Builds on

23 of 61 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Causal Reasoning and Large Language Models: Opening a New Frontier for Causality28 Apr

Other references · 22

  1. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  2. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  3. 2019Fine-Tuning Language Models from Human Preferencescited by 2,124
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  5. 2024Large Language Models for Mathematical Reasoning: Progresses and Challengescited by 283
  6. 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Taskscited by 243
  7. 2023Fine-tuning Language Models for Factualitycited by 219
  8. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  9. 2020A Distributional Approach to Controlled Text Generationcited by 117
  10. 2024Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoningcited by 69
  11. 2023Understanding Causality with Large Language Models: Feasibility and Opportunitiescited by 53
  12. 2024FLAME: Factuality-Aware Alignment for Large Language Modelscited by 46
10 more
  1. 2021CRASS: A Novel Data Set and Benchmark to Test Counterfactual Reasoning of Large Language Modelscited by 33
  2. 2024LLMs for Generating and Evaluating Counterfactuals: A Comprehensive Studycited by 30
  3. 2019Sample Efficient Text Summarization Using a Single Pre-Trained Transformercited by 27
  4. 2024Cause and Effect: Can Large Language Models Truly Understand Causality?cited by 23
  5. 2023Dialectical language model evaluation: An initial appraisal of the commonsense spatial reasoning abilities of LLMscited by 20
  6. 2023Large language models for aspect-based sentiment analysiscited by 17
  7. 2024Look Before You Decide: Prompting Active Deduction of MLLMs for Assumptive Reasoningcited by 17
  8. 2024Optimizing Language Models for Human Preferences is a Causal Inference Problemcited by 8
  9. 2024Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Modelscited by 8
  10. 2023TRIALSCOPE: A Unifying Causal Framework for Scaling Real-World Evidence Generation with Biomedical Language Modelscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 7; 2026: 7.

14 papers.

Sort:

By area:

  1. 2025Causal Sufficiency and Necessity Improves Chain-of-Thought Reasoningcited by 16
  2. 2025RE-IMAGINE: Symbolic Benchmark Synthesis for Reasoning Evaluationcited by 11
  3. 2025Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Codecited by 10
  4. 2025Compositional Causal Reasoning Evaluation in Language Modelscited by 6
  5. 2025CausalARC: Abstract Reasoning with Causal World Modelscited by 4
  6. 2026FACT-E: Causality-Inspired Evaluation for Trustworthy Chain-of-Thought Reasoningcited by 3
  7. 2025How Well Do LLMs Understand Drug Mechanisms? A Knowledge + Reasoning Evaluation Datasetcited by 1
  8. 2026Omitted Variable Bias in Language Models Under Distribution Shiftcited by 1
  9. 2025Mitigating Hidden Confounding by Progressive Confounder Imputation via Large Language Modelscited by 0
  10. 2026Better Think Thrice: Learning to Reason Causally with Double Counterfactual Consistencycited by 0
  11. 2026CauSim: Scaling Causal Reasoning with Increasingly Complex Causal Simulatorscited by 0
  12. 2026Position: Reasoning is a Learnable Rule-Based Processcited by 0
2 more
  1. 2026Beyond Appearance Shifts: Task-Semantic Action Calibration for VLA Modelscited by 0
  2. 2026Is This Evidence Decision-Critical? Learning to Verify Rule-Governed Decisionscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025On the Eligibility of LLMs for Counterfactual Reasoning: A Decompositional Study
  2. 2025CounterBench: Evaluating and Improving Counterfactual Reasoning in Large Language Models
  3. 2026Towards Generalizable Reasoning: Group Causal Counterfactual Policy Optimization for LLM Reasoning
  4. 2025Causal Consistency Regularization: Training Verifiably Sensitive Reasoning in Large Language Models
  5. 2023CLOMO: Counterfactual Logical Modification with Large Language Models
  6. 2024MalAlgoQA: Pedagogical Evaluation of Counterfactual Reasoning in Large Language Models and Implications for AI in Education
  7. 2026The Illusion of textitWhat If: Evaluating the Breakdown of Counterfactual Reasoning in LLMs
  8. 2025Flying Pigs, FaR and Beyond: Evaluating LLM Reasoning in Counterfactual Worlds