# RECKONING: Reasoning through Dynamic Knowledge Encoding

arXiv: https://arxiv.org/abs/2305.06349 · HTML: https://mlsanity.com/paper/2305.06349/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 62 of its 88 references that are in the map.
- First posted on arXiv 10 May 2023.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)

## Builds on (most cited first, 30 of 62)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Language Models as Knowledge Bases?](https://mlsanity.com/paper/1909.01066/) (2019)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [How Can We Know What Language Models Know?](https://mlsanity.com/paper/1911.12543/) (2019)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [A Primer in BERTology: What we know about how BERT works](https://mlsanity.com/paper/2002.12327/) (2020)
- [Quantifying Memorization Across Neural Language Models](https://mlsanity.com/paper/2202.07646/) (2022)
- [How Much Knowledge Can You Pack Into the Parameters of a Language Model?](https://mlsanity.com/paper/2002.08910/) (2020)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Measuring and Improving Consistency in Pretrained Language Models](https://mlsanity.com/paper/2102.01017/) (2021)
- [ProofWriter: Generating Implications, Proofs, and Abductive Statements over Natural Language](https://mlsanity.com/paper/2012.13048/) (2020)
- [How to train your MAML](https://mlsanity.com/paper/1810.09502/) (2018)
- [Abductive Commonsense Reasoning](https://mlsanity.com/paper/1908.05739/) (2019)
- [Generate rather than Retrieve: Large Language Models are Strong Context Generators](https://mlsanity.com/paper/2209.10063/) (2022)
- [Transformers as Soft Reasoners over Language](https://mlsanity.com/paper/2002.05867/) (2020)
- [COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs](https://mlsanity.com/paper/2010.05953/) (2020)
- [FOLIO: Natural Language Reasoning with First-Order Logic](https://mlsanity.com/paper/2209.00840/) (2022)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [Evaluating the Logical Reasoning Ability of ChatGPT and GPT-4](https://mlsanity.com/paper/2304.03439/) (2023)

## Built on by (most cited first, 18 of 18)

- [Adapting Large Language Models to Domains via Reading Comprehension](https://mlsanity.com/paper/2309.09530/) (2023)
- [Towards a Mechanistic Interpretation of Multi-Step Reasoning Capabilities of Language Models](https://mlsanity.com/paper/2310.14491/) (2023)
- [How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances](https://mlsanity.com/paper/2310.07343/) (2023)
- [CAR: Conceptualization-Augmented Reasoner for Zero-Shot Commonsense Question Answering](https://mlsanity.com/paper/2305.14869/) (2023)
- [LeanReasoner: Boosting Complex Logical Reasoning with Lean](https://mlsanity.com/paper/2403.13312/) (2024)
- [CodeUpdateArena: Benchmarking Knowledge Editing on API Updates](https://mlsanity.com/paper/2407.06249/) (2024)
- [Discovering Knowledge-Critical Subnetworks in Pretrained Language Models](https://mlsanity.com/paper/2310.03084/) (2023)
- [Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neurons](https://mlsanity.com/paper/2408.03247/) (2024)
- [MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning](https://mlsanity.com/paper/2505.16225/) (2025)
- [Mechanistic Unveiling of Transformer Circuits: Self-Influence as a Key to Model Reasoning](https://mlsanity.com/paper/2502.09022/) (2025)
- [A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future](https://mlsanity.com/paper/2412.14056/) (2024)
- [Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction](https://mlsanity.com/paper/2404.17809/) (2024)
- [Breaking the Language Barrier: Improving Cross-Lingual Reasoning with Structured Self-Attention](https://mlsanity.com/paper/2310.15258/) (2023)
- [PropMEND: Hypernetworks for Knowledge Propagation in LLMs](https://mlsanity.com/paper/2506.08920/) (2025)
- [TrustMargin: Training-Free Arbitration between Parametric Memory and Retrieved Evidence in Large Language Models](https://mlsanity.com/paper/2606.08397/) (2026)
- [ESG-Bench: Benchmarking Long-Context ESG Reports for Hallucination Mitigation](https://mlsanity.com/paper/2603.13154/) (2026)
- [Retrievable Gradients: Continual Post-Training Without Cumulative Weight Drift](https://mlsanity.com/paper/2606.15734/) (2026)
- [Encoding Context into LLM Weights: What Makes It Context?](https://mlsanity.com/paper/2610.17686/) (2026)

## Abstract (arXiv)

Recent studies on transformer-based language models show that they can answer questions by reasoning over knowledge provided as part of the context (i.e., in-context reasoning). However, since the available knowledge is often not filtered for a particular question, in-context reasoning can be sensitive to distractor facts, additional content that is irrelevant to a question but that may be relevant for a different question (i.e., not necessarily random noise). In these situations, the model fails to distinguish the knowledge that is necessary to answer the question, leading to spurious reasoning and degraded performance. This reasoning failure contrasts with the model's apparent ability to distinguish its contextual knowledge from all the knowledge it has memorized during pre-training. Following this observation, we propose teaching the model to reason more robustly by folding the provided contextual knowledge into the model's parameters before presenting it with a question. Our method, RECKONING, is a bi-level learning algorithm that teaches language models to reason by updating their parametric knowledge through back-propagation, allowing them to then answer questions using the updated parameters. During training, the inner loop rapidly adapts a copy of the model weights to encode contextual knowledge into its parameters. In the outer loop, the model learns to use the updated weights to reproduce and answer reasoning questions about the memorized knowledge. Our experiments on two multi-hop reasoning datasets show that RECKONING's performance improves over the in-context reasoning baseline (by up to 4.5%). We also find that compared to in-context reasoning, RECKONING generalizes better to longer reasoning chains unseen during training, is more robust to distractors in the context, and is more computationally efficient when multiple questions are asked about the same knowledge.