Less Is More? Examining Fairness in Pruned Large Language Models for Summarising Opinions (2025.emnlp-main)
Copied to clipboard
| Challenge: | reducing the size of LLMs through post-training pruning has been studied, but its impact on model fairness remains unexplored. |
| Approach: | They propose a pruning method that removes parameters that are redundant for input processing but influential in output generation. |
| Outcome: | The proposed pruning method can maintain or improve fairness across models and tasks where existing methods have limitations. |
Similar Papers
Rethinking Pruning Large Language Models: Benefits and Pitfalls of Reconstruction Error Minimization (2024.emnlp-main)
Copied to clipboard
| Challenge: | minimizing reconstruction error is not always ideal and can overfit calibration data. |
| Approach: | They propose a method to prune large language models by divide and conquer . they propose minimizing reconstruction error by more than 90% by using calibration data . |
| Outcome: | The proposed pruning approach generates high reconstruction errors . the proposed technique reduces reconstruction error by more than 90% . |
A Comparative Study on the Impact of Model Compression Techniques on Fairness in Language Models (2023.acl-long)
Copied to clipboard
| Challenge: | Existing literature demonstrates that compressing deep learning models could affect their fairness. |
| Approach: | They evaluate pruned, distilled, and quantized language models to assess their fairness . they also examine the impact of using multilingual models and evaluation measures . |
| Outcome: | The proposed methods can reduce the fairness of language models by reducing their complexity and reducing the cost of training and deployment. |
Fair Abstractive Summarization of Diverse Perspectives (2024.naacl-long)
Copied to clipboard
Yusen Zhang, Nan Zhang, Yixin Liu, Alexander Fabbri, Junru Liu, Ryo Kamoi, Xiaoxin Lu, Caiming Xiong, Jieyu Zhao, Dragomir Radev, Kathleen McKeown, Rui Zhang
| Challenge: | Existing work on summarization metrics and large language models has not explored fair abstractive summarizing. |
| Approach: | They propose four reference-free automatic metrics to measure the differences between target and source perspectives. |
| Outcome: | The proposed methods alleviate fair abstractive summarization on user-generated data. |
On the Limitations of Language-targeted Pruning: Investigating the Calibration Language Impact in Multilingual LLM Pruning (2026.tacl-1)
Copied to clipboard
| Challenge: | Recent advances in large language model pruning have shown high predictive performance in post-training settings. |
| Approach: | They conduct an empirical study on the performance and internal representation changes associated with pruning multilingual models for monolingual applications. |
| Outcome: | The proposed pruning methods retain perplexity and yield high signal-to-noise ratios, but not consistently improve downstream tasks. |
As easy as PIE: understanding when pruning causes language models to disagree (2025.findings-naacl)
Copied to clipboard
| Challenge: | Language Model pruning reduces the model's efficiency by removing weights, nodes, or other parts of its architecture. |
| Approach: | They propose to prune Language Models (LMs) to produce smaller, hence more efficient models with small loss to their effectiveness. |
| Outcome: | The proposed pruning method hurts data points that matter the most when pruning . the proposed pruning technique is based on a new study of NLP datasets . |
When Bigger Isn’t Better: A Comprehensive Fairness Evaluation of Political Bias in Multi-News Summarisation (2026.acl-long)
Copied to clipboard
| Challenge: | Existing models that deal with multiple sources can exhibit political biases, causing unequal representation of viewpoints and underrepresentation of minority voices. |
| Approach: | They examine how large language models handle sources with varying political leanings using a dataset with political orientation labels. |
| Outcome: | The proposed model outperforms larger models and offers the best balance of fairness and efficiency. |
Fairness Evaluation and Inference Level Mitigation in LLMs (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, and the propagation of unwanted patterns during extended dialogues. |
| Approach: | They propose a pruning-based framework that detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation. |
| Outcome: | The proposed framework detects context-aware neuron activations and applies adaptive masking to modulate their influence during generation. |
Structured Pruning of Large Language Models (2020.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in language modeling have led to remarkable improvements on a variety of tasks. |
| Approach: | They propose a generic, structured pruning approach by parameterizing each weight matrix and adaptively removing rank-1 components during training. |
| Outcome: | The proposed method outperforms unstructured pruning and block pruning on language modeling tasks while achieving speedups during training and inference. |
On the Impact of Calibration Data in Post-training Quantization and Pruning (2024.acl-long)
Copied to clipboard
| Challenge: | Quantization and pruning are the foundations of compression for large language models . however, no prior work has investigated how calibration data impacts performance of compression methods. |
| Approach: | They propose an empirical study on the effect of calibration data on LLM performance. |
| Outcome: | The proposed methods improve performance in a post-training setting. |
DRPruning: Efficient Large Language Model Pruning through Distributionally Robust Optimization (2025.acl-long)
Copied to clipboard
| Challenge: | Structured pruning reduces model size but often causes uneven degradation across domains, leading to biased performance. |
| Approach: | They propose a method that dynamically adjusts the data distribution during training to restore balanced performance across heterogeneous and multi-tasking data. |
| Outcome: | Experiments in monolingual and multilingual settings show that the proposed method surpasses similarly sized models in pruning and continued pretraining over perplexity, downstream tasks, and instruction tuning. |