Challenge: Large language models have shown impressive few-shot in-context learning abilities, but they are prone to a ‘copying bias’, where they copy answers from provided examples instead of learning the underlying patterns.
Approach: They propose a method to prune neurons that prioritize copying over generalization and adopt a task-recognition perspective on ICL and examine task vectors induced by the model.
Outcome: The proposed method improves performance across a diverse set of ICL tasks while maintaining or improving the model’s general capabilities.

Similar Papers

Toward Inclusive Language Models: Sparsity-Driven Calibration for Systematic and Interpretable Mitigation of Social Biases in LLMs (2025.findings-emnlp)

Copied to clipboard

Challenge: a new method to mitigate stereotypical bias in large language models is needed . inherent biases from training on vast Internet datasets can amplify harmful stereotypes .
Approach: They propose a method to identify stereotypical bias in decoder-only transformer models . they apply a localization mechanism that correlates internal activations with a new Context Influence score .
Outcome: The proposed method reduces stereotypical biases on BBQ, StereoSet, and CrowS-Pairs while improving reasoning performance on MMLU by 10%.
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.
In-Context Learning Creates Task Vectors (2023.findings-emnlp)

Copied to clipboard

Challenge: In-context learning (ICL) is a powerful new learning paradigm for Large Language Models (LLMs).
Approach: They propose to use a model with a prompt and a query to learn a mapping based on two examples to produce the output.
Outcome: The proposed model can learn functions from a simple structure based on a training set and a single task vector calculated from the training set.
BlockPruner: Fine-grained Pruning for Large Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have significant computational and memory costs associated with training and inference.
Approach: They propose a training-free structured pruning approach that targets redundancies in MHA and MLP blocks.
Outcome: The proposed pruning approach achieves more granular and effective pruning compared to state-of-the-art pruning methods.
Mitigating Label Biases for In-context Learning (2023.acl-long)

Copied to clipboard

Challenge: Existing methods to categorize label biases in in-context learning (ICL) have not addressed all three types of label bias.
Approach: They propose a method that estimates a language model’s label bias using random in-domain words from the task corpus to categorize and detect label biases in ICL.
Outcome: The proposed method significantly improves the performance of GPT-J and GPT-3 on a wide range of tasks.
Gradient-based Intra-attention Pruning on Pre-trained Language Models (2023.acl-long)

Copied to clipboard

Challenge: Pre-trained language models are computationally expensive and slow in inference due to their large sizes.
Approach: They propose a structured pruning method which combines pruning with knowledge distillation to yield highly effective models.
Outcome: The proposed method outperforms other pruning methods in sparsity regimes while maintaining 93% 99% performance.
Imbalanced Gradients in RL Post-Training of Multi-Task LLMs (2026.findings-eacl)

Copied to clipboard

Challenge: Large-gradient tasks can achieve similar or even much lower learning gains than small-grading ones.
Approach: They show that large-gradient tasks can achieve lower learning gains than small-grading ones . large-grade tasks can accomplish similar or even lower learning gain than small grade ones if they are large .
Outcome: The proposed approach fails when certain tasks produce larger gradients . Large-gradient tasks can achieve lower learning gains than small-gradent ones .
Beyond Generation: Leveraging LLM Creativity to Overcome Label Bias in Classification (2025.findings-acl)

Copied to clipboard

Challenge: Existing methods to mitigate label bias by leveraging in-domain data are often unavailable in real-world scenarios.
Approach: They propose a calibration method that generates synthetic in-domain data from a few in-context demonstrations and utilizes it for calibration.
Outcome: The proposed method reduces label bias by leveraging in-domain data from demonstrations.
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% .
Task-aware Block Pruning with Output Distribution Signals for Large Language Models (2026.findings-eacl)

Copied to clipboard

Challenge: Existing methods to estimate block importance rely on representation similarity or computationally expensive sensitivity analyses to estimate task-aware model behavior.
Approach: They propose a novel approach that quantifies block-level uncertainty from the statistics of each block’s early-exited output distribution on a calibration dataset.
Outcome: Experiments show that the proposed approach preserves downstream task performance while reducing inference latency and computational cost.

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