Challenge: Using a new fine-tuning loss, we show that inner neurons with diverse outgoing connections are more critical to model performance than those with uniform connections.
Approach: They propose a new loss that reduces the outgoing connection entropy in feedforward layers and elucidates the role of outgoing connections in large language models.
Outcome: The proposed method is significantly more effective than removing neurons randomly or based on their magnitude.

Similar Papers

From Distributional to Overton Pluralism: Investigating Large Language Model Alignment (2025.naacl-long)

Copied to clipboard

Challenge: a large language model's (LLM) output distribution is changed by an alignment process . a recent study shows that aligned models surface information that cannot be recovered from base models without fine-tuning.
Approach: They analyze two aspects of the alignment process that change output distributions . they find alignment suppresses irrelevant and unhelpful content .
Outcome: The proposed model can be imitated without fine-tuning by using in-context examples and lower-resolution semantic hints about response content.
Unveiling the Generalization Power of Fine-Tuned Large Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Large Language Models (LLMs) have demonstrated exceptional multitasking abilities, but the comprehensive effects of fine-tuning on the LLMs’ generalization ability are not fully understood.
Approach: They conduct extensive experiments across five distinct language tasks on different datasets to investigate whether fine-tuning affects the generalization ability intrinsic to LLMs.
Outcome: The proposed model can generalize to different domains and tasks by integrating the in-context learning strategy during fine-tuning on generation tasks.
The Effect of Language Diversity When Fine-Tuning Large Language Models for Translation (2025.findings-emnlp)

Copied to clipboard

Challenge: Prior research on language diversity in LLM fine-tuning has reported benefits while others find no benefits.
Approach: They find that expanding language diversity during fine-tuning improves translation quality . they also show that increased language diversity creates more language-agnostic representations .
Outcome: The proposed model improves translation quality for unsupervised and supervised pairs . the results plateau or decrease beyond a certain diversity threshold.
Disentangling Linguistic Relatedness from Task Alignment in Cross-Lingual Transfer (2026.acl-srw)

Copied to clipboard

Challenge: Large language models (LLMs) have advanced natural language processing, yet their benefits remain concentrated in English and a small number of high-resource languages.
Approach: They fine-tuned large language models (4B–671B parameters) on Arabic and evaluated zero-shot reading comprehension on Semitic languages and non-Semitic controls.
Outcome: The results show that models with weak baselines improve across all languages, whereas strong-baseline models show only marginal gains regardless of language family.
Let’s Focus on Neuron: Neuron-Level Supervised Fine-tuning for Large Language Model (2025.coling-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) are composed of neurons that exhibit diverse behaviors and roles.
Approach: They propose a novel approach that refines the granularity of parameter training down to the individual neuron, enabling a more parameter-efficient fine-tuning model.
Outcome: The proposed approach exceeds the performance of full-parameter fine-tuning and PEFT and provides insights into the analysis of neurons.
Understanding the effects of language-specific class imbalance in multilingual fine-tuning (2024.findings-eacl)

Copied to clipboard

Challenge: Existing methods to fine-tune large language models have been developed to reduce the amount of resources needed to perform classification tasks.
Approach: They modify traditional class weighing approach to reduce imbalance by calculating class weights separately for each language.
Outcome: The proposed model improves performance and reduces the promotion of uninformative features.
Exploring Anisotropy and Outliers in Multilingual Language Models for Cross-Lingual Semantic Sentence Similarity (2023.findings-acl)

Copied to clipboard

Challenge: Recent studies have shown that contextual language models display outlier dimensions . this is true for monolingual and multilingual models, but little work has been done on multilingual contexts .
Approach: They investigate outlier dimensions and their relationship to anisotropy in multilingual contexts . they focus on cross-lingual semantic similarity tasks .
Outcome: The proposed model improves on cross-lingual semantic similarity tasks.
Attention Entropy is a Key Factor: An Analysis of Parallel Context Encoding with Full-attention-based Pre-trained Language Models (2025.acl-long)

Copied to clipboard

Challenge: Large language models have demonstrated remarkable performance across a wide range of language tasks due to their remarkable ability in context modeling.
Approach: They propose to use parallel context encoding to reduce attention entropy by incorporating attention sinks and selective mechanisms to reduce irregular attention . they also propose to incorporate attention sink mechanisms into the parallel encoded context to reduce the irregular attention.
Outcome: The proposed methods lower irregular attention entropy and narrow performance gaps.
Data and Parameter Scaling Laws for Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Recent work shows that supervised neural machine translation models scale like a power law with the amount of training data and number of non-embedding parameters in the model.
Approach: They show that cross-entropy loss of supervised neural machine translation models scales like a power law with the amount of training data and number of non-embedding parameters in the model.
Outcome: The proposed model can predict BLEU and ROI of labeling data in low-resource language pairs.
Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs (2025.acl-long)

Copied to clipboard

Challenge: Effective cross-lingual transfer is hindered by performance gaps and the scarcity of fine-tuning data in many languages.
Approach: They propose a middle-layer alignment objective integrated into task-specific training to improve cross-lingual transfer across languages.
Outcome: The proposed method improves cross-lingual transfer to lower-resource languages and can be merged with existing modules without full re-training.

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