# Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning

arXiv: https://arxiv.org/abs/2010.05906 · HTML: https://mlsanity.com/paper/2010.05906/

## Key facts

- Cited by 65 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Oct 2020.

## Built on by (most cited first, 30 of 65)

- [Diffusion-LM Improves Controllable Text Generation](https://mlsanity.com/paper/2205.14217/) (2022)
- [Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task](https://mlsanity.com/paper/2210.13382/) (2022)
- [Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks](https://mlsanity.com/paper/2307.02477/) (2023)
- [COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability](https://mlsanity.com/paper/2402.08679/) (2024)
- [COLD Decoding: Energy-based Constrained Text Generation with Langevin Dynamics](https://mlsanity.com/paper/2202.11705/) (2022)
- [The Perils of Using Mechanical Turk to Evaluate Open-Ended Text Generation](https://mlsanity.com/paper/2109.06835/) (2021)
- [Detoxifying Large Language Models via Knowledge Editing](https://mlsanity.com/paper/2403.14472/) (2024)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Probing Across Time: What Does RoBERTa Know and When?](https://mlsanity.com/paper/2104.07885/) (2021)
- [Controlled Text Generation as Continuous Optimization with Multiple Constraints](https://mlsanity.com/paper/2108.01850/) (2021)
- [Gradient-Based Constrained Sampling from Language Models](https://mlsanity.com/paper/2205.12558/) (2022)
- [Natural Language Reasoning, A Survey](https://mlsanity.com/paper/2303.14725/) (2023)
- [ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification](https://mlsanity.com/paper/2203.02225/) (2022)
- [KCTS: Knowledge-Constrained Tree Search Decoding with Token-Level Hallucination Detection](https://mlsanity.com/paper/2310.09044/) (2023)
- [Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey](https://mlsanity.com/paper/2201.12438/) (2022)
- [The Abduction of Sherlock Holmes: A Dataset for Visual Abductive Reasoning](https://mlsanity.com/paper/2202.04800/) (2022)
- [Inference-Time Policy Adapters (IPA): Tailoring Extreme-Scale LMs without Fine-tuning](https://mlsanity.com/paper/2305.15065/) (2023)
- [DeepEdit: Knowledge Editing as Decoding with Constraints](https://mlsanity.com/paper/2401.10471/) (2024)
- [Composable Text Controls in Latent Space with ODEs](https://mlsanity.com/paper/2208.00638/) (2022)
- [GENIE: Toward Reproducible and Standardized Human Evaluation for Text Generation](https://mlsanity.com/paper/2101.06561/) (2021)
- [On the Limitations of Dataset Balancing: The Lost Battle Against Spurious Correlations](https://mlsanity.com/paper/2204.12708/) (2022)
- [Unsupervised Enrichment of Persona-grounded Dialog with Background Stories](https://mlsanity.com/paper/2106.08364/) (2021)
- [Counterfactual Token Generation in Large Language Models](https://mlsanity.com/paper/2409.17027/) (2024)
- [COINS: Dynamically Generating COntextualized Inference Rules for Narrative Story Completion](https://mlsanity.com/paper/2106.02497/) (2021)
- [Knowledge Infused Decoding](https://mlsanity.com/paper/2204.03084/) (2022)
- [LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM Reasoning](https://mlsanity.com/paper/2502.11176/) (2025)
- [Element Intervention for Open Relation Extraction](https://mlsanity.com/paper/2106.09558/) (2021)
- [Abductive Commonsense Reasoning Exploiting Mutually Exclusive Explanations](https://mlsanity.com/paper/2305.14618/) (2023)
- [Controllable Logical Hypothesis Generation for Abductive Reasoning in Knowledge Graphs](https://mlsanity.com/paper/2505.20948/) (2025)
- [Transferable Persona-Grounded Dialogues via Grounded Minimal Edits](https://mlsanity.com/paper/2109.07713/) (2021)

## Abstract (arXiv)

Abductive and counterfactual reasoning, core abilities of everyday human cognition, require reasoning about what might have happened at time t, while conditioning on multiple contexts from the relative past and future. However, simultaneous incorporation of past and future contexts using generative language models (LMs) can be challenging, as they are trained either to condition only on the past context or to perform narrowly scoped text-infilling. In this paper, we propose DeLorean, a new unsupervised decoding algorithm that can flexibly incorporate both the past and future contexts using only off-the-shelf, left-to-right language models and no supervision. The key intuition of our algorithm is incorporating the future through back-propagation, during which, we only update the internal representation of the output while fixing the model parameters. By alternating between forward and backward propagation, DeLorean can decode the output representation that reflects both the left and right contexts. We demonstrate that our approach is general and applicable to two nonmonotonic reasoning tasks: abductive text generation and counterfactual story revision, where DeLorean outperforms a range of unsupervised and some supervised methods, based on automatic and human evaluation.