Generating Repetitions with Appropriate Repeated Words (2022.naacl-main)

Copied to clipboard

Challenge: Existing studies have focused on general response generation with neural network-based approaches, but none have addressed specific types of repetitions.
Approach: They propose a weighted label smoothing method for explicitly learning which words to repeat during fine-tuning and a repetition scoring method that can output more appropriate repetitions during decoding.
Outcome: The proposed method outperforms baselines in automatic and human evaluations on a pre-trained language model for generating repetitions.

Similar Papers

Repetition Neurons: How Do Language Models Produce Repetitions? (2025.naacl-short)

Copied to clipboard

Challenge: Existing studies on text generation with LLMs focus on attention heads, framing repetition as a key mechanism for in-context learning.
Approach: They introduce repetition neurons that are regarded as "skill neurons" responsible for the repetition problem in text generation tasks.
Outcome: The authors identify repetition neurons as "skill neurons" that perceive repetition as a task to copy the previous context repeatedly, similar to in-context learning.
Implicit Unlikelihood Training: Improving Neural Text Generation with Reinforcement Learning (2021.eacl-main)

Copied to clipboard

Challenge: Existing approaches to language modeling use autoregressive methods, but they can produce repetitive results.
Approach: They propose to add a loss function for regularization to avoid unwanted properties, such as contradiction or repetition, to a language model by using policy gradient reinforcement learning.
Outcome: The proposed method reduces repetition without impacting the language model quality.
Towards Less Generic Responses in Neural Conversation Models: A Statistical Re-weighting Method (D18-1)

Copied to clipboard

Challenge: Experimental results show that Sequence-to-sequence models tend to generate generic/dull responses .
Approach: They propose a statistical re-weighting method that assigns different weights for multiple responses of the same query.
Outcome: The proposed method improves acceptance rate of generated responses and significantly reduces generated generic responses.
Self-Repetition in Abstractive Neural Summarizers (2022.aacl-short)

Copied to clipboard

Challenge: a quantitative and qualitative analysis of self-repetition in neural summarization systems is needed to improve training.
Approach: They propose a quantitative and qualitative analysis of self-repetition in neural summarization systems . they analyze the behavior of three popular architectures fine-tuned on five datasets .
Outcome: The proposed model produces formulaic repetition in summaries, but not in summarization tasks.
A Systematic Review of Reproducibility Research in Natural Language Processing (2021.eacl-main)

Copied to clipboard

Challenge: Despite the recent progress in reproducibility, the field is far from reaching a consensus on how reproducibility should be defined, measured and addressed.
Approach: They propose to provide a wide-angle snapshot of current work on reproducibility in NLP.
Outcome: The proposed work will provide a wide-angle snapshot of current work on reproducibility in NLP.
Mitigating the Learning Bias towards Repetition by Self-Contrastive Training for Open-Ended Generation (2023.findings-acl)

Copied to clipboard

Challenge: Existing language models generate repetitive texts with greedy decoding or beam search.
Approach: They propose a self-contrastive training technique to penalize the output of a premature checkpoint of the same model when it incorrectly predicts repetition.
Outcome: The proposed training mitigates repetition while maintaining fluency while minimizing the overestimation of token-level repetition probabilities.
Penalty Decoding: Well Suppress the Self-Reinforcement Effect in Open-Ended Text Generation (2023.emnlp-main)

Copied to clipboard

Challenge: Experimental results demonstrate the efficacy of our approach in generating high-quality sentences resembling human output.
Approach: They propose a forgetting mechanism that disregards distant tokens, reducing the burden of penalty selection.
Outcome: The proposed approach generates high-quality sentences resembling human output.
Rethinking Repetition Problems of LLMs in Code Generation (2025.acl-long)

Copied to clipboard

Challenge: Recent studies have focused on content repetition, but structural repetition is a more prevalent problem in code generation.
Approach: They propose a decoding approach that eliminates repetition problems in code generation by identifying grammar rules and strategically decaying the likelihood of critical tokens that contribute to repetitions.
Outcome: The proposed approach outperforms baselines and humanEval benchmarks on CodeRepetEval dataset and MBPP benchmarks, effectively reducing repetitions and enhancing the quality of generated code.
Multi-Reference Training with Pseudo-References for Neural Translation and Text Generation (D18-1)

Copied to clipboard

Challenge: Neural text generation has been quite successful recently, but during training time, only one reference is considered for each example, even though there are often multiple references available.
Approach: They propose an algorithm to generate exponentially many pseudo-references by compressing existing references into lattices and traversing them to generate new pseudo-References.
Outcome: The proposed model significantly improves on baselines in machine translation and image captioning, and is comparable to existing models.
Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Neural machine translation (NMT) uses a sequence-to-sequence model to generate synthetic data.
Approach: They propose a method that adds synthetic data to sentences with high prediction loss during training and a variety of sampling strategies targeting difficult-to-predict words.
Outcome: The proposed method improves translation quality by up to 1.7 and 1.2 Bleu points over back-translation using random sampling for German-English and English-German, respectively.

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