# Can LMs Learn New Entities from Descriptions? Challenges in Propagating Injected Knowledge

arXiv: https://arxiv.org/abs/2305.01651 · HTML: https://mlsanity.com/paper/2305.01651/

## Key facts

- Cited by 67 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 2 May 2023.

## Builds on (most cited first, 21 of 21)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Knowledge Neurons in Pretrained Transformers](https://mlsanity.com/paper/2104.08696/) (2021)
- [Editing Factual Knowledge in Language Models](https://mlsanity.com/paper/2104.08164/) (2021)
- [Fast Model Editing at Scale](https://mlsanity.com/paper/2110.11309/) (2021)
- [Large Language Models Struggle to Learn Long-Tail Knowledge](https://mlsanity.com/paper/2211.08411/) (2022)
- [Time-Aware Language Models as Temporal Knowledge Bases](https://mlsanity.com/paper/2106.15110/) (2021)
- [Mind the Gap: Assessing Temporal Generalization in Neural Language Models](https://mlsanity.com/paper/2102.01951/) (2021)
- [Modifying Memories in Transformer Models](https://mlsanity.com/paper/2012.00363/) (2020)
- [Towards Continual Knowledge Learning of Language Models](https://mlsanity.com/paper/2110.03215/) (2021)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [SituatedQA: Incorporating Extra-Linguistic Contexts into QA](https://mlsanity.com/paper/2109.06157/) (2021)
- [TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Models](https://mlsanity.com/paper/2204.14211/) (2022)
- [Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora](https://mlsanity.com/paper/2110.08534/) (2021)
- [Entity Cloze By Date: What LMs Know About Unseen Entities](https://mlsanity.com/paper/2205.02832/) (2022)
- [Prompt Injection: Parameterization of Fixed Inputs](https://mlsanity.com/paper/2206.11349/) (2022)
- [Probing Factually Grounded Content Transfer with Factual Ablation](https://mlsanity.com/paper/2203.10133/) (2022)

## Built on by (most cited first, 30 of 67)

- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Editing Large Language Models: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2305.13172/) (2023)
- [MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions](https://mlsanity.com/paper/2305.14795/) (2023)
- [Knowledge Conflicts for LLMs: A Survey](https://mlsanity.com/paper/2403.08319/) (2024)
- [Evaluating the Ripple Effects of Knowledge Editing in Language Models](https://mlsanity.com/paper/2307.12976/) (2023)
- [Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategies](https://mlsanity.com/paper/2308.03188/) (2023)
- [Knowledge Editing for Large Language Models: A Survey](https://mlsanity.com/paper/2310.16218/) (2023)
- [Do Large Language Models Latently Perform Multi-Hop Reasoning?](https://mlsanity.com/paper/2402.16837/) (2024)
- [A Comprehensive Study of Knowledge Editing for Large Language Models](https://mlsanity.com/paper/2401.01286/) (2024)
- [BadEdit: Backdooring large language models by model editing](https://mlsanity.com/paper/2403.13355/) (2024)
- [Can Knowledge Graphs Reduce Hallucinations in LLMs? : A Survey](https://mlsanity.com/paper/2311.07914/) (2023)
- [Hopping Too Late: Exploring the Limitations of Large Language Models on Multi-Hop Queries](https://mlsanity.com/paper/2406.12775/) (2024)
- [Can We Edit Multimodal Large Language Models?](https://mlsanity.com/paper/2310.08475/) (2023)
- [In-Context Editing: Learning Knowledge from Self-Induced Distributions](https://mlsanity.com/paper/2406.11194/) (2024)
- [How Do Large Language Models Capture the Ever-changing World Knowledge? A Review of Recent Advances](https://mlsanity.com/paper/2310.07343/) (2023)
- [Genie: Achieving Human Parity in Content-Grounded Datasets Generation](https://mlsanity.com/paper/2401.14367/) (2024)
- [Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two Benchmarks](https://mlsanity.com/paper/2311.09060/) (2023)
- [Editing Common Sense in Transformers](https://mlsanity.com/paper/2305.14956/) (2023)
- [Propagating Knowledge Updates to LMs Through Distillation](https://mlsanity.com/paper/2306.09306/) (2023)
- [Do Large Language Models Perform Latent Multi-Hop Reasoning without Exploiting Shortcuts?](https://mlsanity.com/paper/2411.16679/) (2024)
- [Emptying the Ocean with a Spoon: Should We Edit Models?](https://mlsanity.com/paper/2310.11958/) (2023)
- [DocTER: Evaluating Document-based Knowledge Editing](https://mlsanity.com/paper/2308.09954/) (2023)
- [Context versus Prior Knowledge in Language Models](https://mlsanity.com/paper/2404.04633/) (2024)
- [Propagation and Pitfalls: Reasoning-based Assessment of Knowledge Editing through Counterfactual Tasks](https://mlsanity.com/paper/2401.17585/) (2024)
- [Fundamental Problems With Model Editing: How Should Rational Belief Revision Work in LLMs?](https://mlsanity.com/paper/2406.19354/) (2024)
- [Overcoming Generic Knowledge Loss with Selective Parameter Update](https://mlsanity.com/paper/2308.12462/) (2023)
- [PokeMQA: Programmable knowledge editing for Multi-hop Question Answering](https://mlsanity.com/paper/2312.15194/) (2023)
- [Controllable Context Sensitivity and the Knob Behind It](https://mlsanity.com/paper/2411.07404/) (2024)
- [MMKE-Bench: A Multimodal Editing Benchmark for Diverse Visual Knowledge](https://mlsanity.com/paper/2502.19870/) (2025)
- [Editing Personality for Large Language Models](https://mlsanity.com/paper/2310.02168/) (2023)

## Abstract (arXiv)

Pre-trained language models (LMs) are used for knowledge intensive tasks like question answering, but their knowledge gets continuously outdated as the world changes. Prior work has studied targeted updates to LMs, injecting individual facts and evaluating whether the model learns these facts while not changing predictions on other contexts. We take a step forward and study LMs' abilities to make inferences based on injected facts (or propagate those facts): for example, after learning that something is a TV show, does an LM predict that you can watch it? We study this with two cloze-style tasks: an existing dataset of real-world sentences about novel entities (ECBD) as well as a new controlled benchmark with manually designed templates requiring varying levels of inference about injected knowledge. Surprisingly, we find that existing methods for updating knowledge (gradient-based fine-tuning and modifications of this approach) show little propagation of injected knowledge. These methods improve performance on cloze instances only when there is lexical overlap between injected facts and target inferences. Yet, prepending entity definitions in an LM's context improves performance across all settings, suggesting that there is substantial headroom for parameter-updating approaches for knowledge injection.