Challenge: Prior studies have shown that kNN-LM can retrieve long-tail contexts, leaving the model’s performance underexplored in estimating the probabilities of long-tailed target tokens.
Approach: They investigate the behavior of kNN-LM on low-frequency tokens, examining prediction probability, retrieval accuracy, and token distribution in the datastore.
Outcome: The proposed model improves the perplexity of given text by directly accessing a large datastore built from any text data during inference.

Similar Papers

Great Memory, Shallow Reasoning: Limits of kNN-LMs (2025.naacl-short)

Copied to clipboard

Challenge: Existing models trained on poor quality data have shown strong performance in language modeling and some downstream benchmarks.
Approach: They evaluate kNN-LMs on a diverse set of tasks and evaluate their performance.
Outcome: The proposed extension could improve on a variety of tasks, but it fails to perform on reasoning tasks that require integrating multiple pieces of information.
Adaptation Approaches for Nearest Neighbor Language Models (2023.findings-acl)

Copied to clipboard

Challenge: Semi-parametric Nearest Neighbor Language Models (kNN-LMs) have produced impressive gains over purely parametric LMs, however, there has been little investigation into adapting such models for new domains.
Approach: They propose to adapt kNN-LMs to expand neighborhood retrieval over an additional adaptation datastore and adapt the weights of retrieved neighbors using a learned Rescorer module.
Outcome: The proposed approach outperforms purely parametric adaptation and zero-shot models and achieves perplexity improvements of 17.1% and 16% across domains.
You can’t pick your neighbors, or can you? When and How to Rely on Retrieval in the kNN-LM (2022.findings-emnlp)

Copied to clipboard

Challenge: Recent studies have shown that retrieval-enhanced language models can improve perplexity by combining text from large external datastores with a k-nearest neighbors model.
Approach: They propose a retrieval-enhanced language model that interpolates existing LMs with a k-nearest neighbors model and requires no additional training.
Outcome: The proposed model improves on two English language modeling datasets and shows that it is most effective when items have high semantic similarity with the query.
Nearest Neighbor Zero-Shot Inference (2022.emnlp-main)

Copied to clipboard

Challenge: Using non-parametric memory for retrieval-augmented language models yields significant performance boosts over strong zeroshot baselines.
Approach: They propose a retrieval-augmented language model with fuzzy verbalizers that expands the verbalizes that define different end-task class labels.
Outcome: The proposed model outperforms non-retrieval-augmented language models on perplexity-based evaluations but gains transfer marginally . the main challenge is to achieve coverage of the verbalizer tokens that define the different end-task class labels.
Efficient Nearest Neighbor Language Models (2021.emnlp-main)

Copied to clipboard

Challenge: Non-parametric neural language models (NLMs) learn text distributions by memorizing training data points.
Approach: They propose to use an external datastore to learn from a non-parametric language model.
Outcome: The proposed methods achieve up to a 6x speed-up in inference speed while retaining comparable performance.
Rescue Implicit and Long-tail Cases: Nearest Neighbor Relation Extraction (2022.emnlp-main)

Copied to clipboard

Challenge: Existing RE models are incapable of handling implicit expressions and long-tail relation types due to language complexity and data sparsity.
Approach: They propose a method to enhance relation extraction using k nearest neighbors (kNN-RE) kNN is a nearest-neighbor search tool that allows the model to consult training relations at test time .
Outcome: The proposed model outperforms the best model to date on ACE05, SciERC, and Wiki80 datasets and outperformed the best on i2b2 and Wik80 dataset.
On Retrieval Augmentation and the Limitations of Language Model Training (2024.naacl-short)

Copied to clipboard

Challenge: Recent efforts to improve the performance of language models (LMs) have focused on scaling up model and training data size, though with steep accompanying energy and compute resource costs.
Approach: They propose to augment a language model with k-nearest neighbors retrieval on its training data to reduce its perplexity.
Outcome: The proposed model reduces storage costs by over 25x compared to traditional retrieval methods for GPT-2 and Mistral 7B .
Chunk-based Nearest Neighbor Machine Translation (2022.emnlp-main)

Copied to clipboard

Challenge: Semi-parametric models augment generation with retrieval, but require expensive retrieval operation for every generated token.
Approach: They propose a semi-parametric model which augments generation with retrieval by retrieving tokens from a datastore.
Outcome: The proposed model can retrieve chunks of tokens from the datastore, instead of a single token, with a low decoding speed.
Regularized Training of Nearest Neighbor Language Models (2022.naacl-srw)

Copied to clipboard

Challenge: kNN-LM uses pre-trained language models and an exhaustive knn search to improve performance.
Approach: They build upon kNN-LM, which uses a pre-trained language model and a knn search through the training data to achieve state-of-the-art results.
Outcome: The proposed method improves on language modeling tasks on WIKI-2 and WIKI-103.
Predicting Numerals in Text Using Nearest Neighbor Language Models (2023.findings-acl)

Copied to clipboard

Challenge: naive language models treat numerals as string tokens, resulting in difficulty in acquiring commonsense . kNN-LM is an extension of pre-trained neural LMs with the k-nearest neighbor (kNN) search .
Approach: They apply k-nearest neighbor LM to a masked numeral prediction task . they found it is effective for fine-grained predictions of numerals from context .
Outcome: The retrieval-based method is effective for fine-grained numeral prediction from context . it improves accuracy for the OOV numerals, the study shows .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations