Papers with gradient-based methods
Zero-Shot Sequence Labeling: Transferring Knowledge from Sentences to Tokens (N18-1)
Copied to clipboard
| Challenge: | Recent work has used attention weights to visualize the focus of neural models in input data. |
| Approach: | They propose to use attention-based visualization techniques to infer token-level labels from a network trained only on sentence-level labeling. |
| Outcome: | The proposed approach outperforms gradient-based methods on four datasets and is expected to outperfect supervised methods. |
Using Interpretation Methods for Model Enhancement (2023.emnlp-main)
Copied to clipboard
| Challenge: | Existing frameworks for enhancing neural models with interpretation methods and gold rationales have not been fully explored. |
| Approach: | They propose a framework for utilizing interpretation methods and gold rationales to enhance neural models. |
| Outcome: | The proposed framework outperforms gradient-based methods in low-resource settings on a variety of tasks. |
Toward Stronger Textual Attack Detectors (2023.findings-emnlp)
Copied to clipboard
| Challenge: | despite the high performance of deep learning techniques, trained models remain vulnerable to adversarial attacks . authors present LAROUSSE, STAKEOUT and other approaches to detect adversarials . LARousSE is unsupervised, hyperparameter free and non-differentiable . |
| Approach: | They propose a framework to detect adversarial attacks and an extended benchmark to test them . they demonstrate that LAROUSSE outperforms previous methods and allows to identify interesting factor of detection rate variations. |
| Outcome: | The proposed framework outperforms existing methods and allows to identify interesting factor of detection rate variations. |
When Gradient Descent Meets Derivative-Free Optimization: A Match Made in Black-Box Scenario (2023.findings-acl)
Copied to clipboard
| Challenge: | Large pre-trained language models (PLMs) are expensive and may not be open-sourced due to commercial considerations and potential risks of misuse. |
| Approach: | They propose to introduce gradient descent into black-box tuning scenario . they propose a method which integrates gradient descent and derivative-free optimization . |
| Outcome: | The proposed method achieves significant performance gains over previous state-of-the-art methods. |
An Empirical Comparison of Instance Attribution Methods for NLP (2021.naacl-main)
Copied to clipboard
| Challenge: | Influence functions provide machinery for identifying training instances that may have led to a specific prediction, but are computationally expensive and prohibitive in many cases. |
| Approach: | They evaluate the degree to which different potential instance attribution agrees with respect to the importance of training samples. |
| Outcome: | The proposed methods exhibit desirable characteristics similar to more complex methods, but are computationally expensive. |
Locally Aggregated Feature Attribution on Natural Language Model Understanding (2022.naacl-main)
Copied to clipboard
| Challenge: | a growing popularity of deep-learning models makes model understanding more important . feature attribution methods have shown promising results in computer vision but are not trivial . |
| Approach: | They propose a gradient-based feature attribution method that smooths gradients by aggregating similar reference texts derived from language model embeddings. |
| Outcome: | The proposed method outperforms existing methods on public datasets and key words detection tasks. |
SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods to generate pre-trained language models with attributes are expensive and overfitted on small training sets. |
| Approach: | They propose a novel approach to control the generation of Transformer-based pre-trained language models using a new control attributes loss framework. |
| Outcome: | The proposed method is shown to perform well with very limited training samples. |
On the Sensitivity and Stability of Model Interpretations in NLP (2022.acl-long)
Copied to clipboard
| Challenge: | Recent years have witnessed the emergence of post-hoc interpretations that aim to uncover how NLP models make predictions. |
| Approach: | They propose two new criteria that provide complementary notions of faithfulness to removal-based criteria. |
| Outcome: | The proposed methods overcome limitations of gradient-based methods on removal-based criteria and overcome limitations in the proposed methods. |
Causal Intersectionality and Dual Form of Gradient Descent for Multimodal Analysis: A Case Study on Hateful Memes (2024.lrec-main)
Copied to clipboard
| Challenge: | Causal analyses define semantics, while gradient-based methods are essential to eXplainable AI (XAI), interpreting the model’s ‘black box’. |
| Approach: | They propose to integrate causal analysis and XAI to integrate a model's mechanisms into their analysis by integrating a dataset of hateful meme detection models. |
| Outcome: | The proposed model can detect hateful memes using intersectionality principles and summarized attention scores highlight distinct behaviors of three Transformer models. |
Can We Edit Factual Knowledge by In-Context Learning? (2023.emnlp-main)
Copied to clipboard
| Challenge: | In-context knowledge editing (IKE) is a new paradigm for NLP research that can be applied to large language models with tens or hundreds of parameters. |
| Approach: | They propose to use in-context knowledge editing (IKE) without gradient updating to edit factual knowledge without a gradient update. |
| Outcome: | The proposed method achieves a competitive success rate compared to gradient-based methods on GPT-J but with fewer side effects. |
BERT-ATTACK: Adversarial Attack Against BERT Using BERT (2020.emnlp-main)
Copied to clipboard
| Challenge: | Current approaches to generate adversarial samples for discrete data are heuristic replacement strategies that are difficult to implement in continuous data. |
| Approach: | They propose a method to generate adversarial samples using pre-trained masked language models using BERT. |
| Outcome: | The proposed method outperforms state-of-the-art methods in success rate and perturb percentage while remaining fluent and semantically preserved. |
Measuring the Mixing of Contextual Information in the Transformer (2022.emnlp-main)
Copied to clipboard
| Challenge: | Experimentally, we show that ALTI provides more faithful explanations and increased robustness than gradient-based methods. |
| Approach: | They propose to measure token-to-token interactions within each layer and then use them to aggregate model predictions. |
| Outcome: | The proposed method provides more faithful explanations and increased robustness than gradient-based methods. |
When Seeing Overrides Knowing: Disentangling Knowledge Conflicts in Vision-Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Vision-language models combine visual and textual information to perform complex tasks. conflicts between internal knowledge and external visual input can lead to hallucinations and unreliable predictions. |
| Approach: | They propose to use a dataset to identify attention heads that deliberately contradict internal commonsense knowledge to resolve cross-modal conflicts. |
| Outcome: | The proposed model can be manipulated to find out which visual inputs are conflicting . the model can then be orientated towards internal parametric knowledge or visual information . |
Toward Human Readable Prompt Tuning: Kubrick’s The Shining is a good movie, and a good prompt too? (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models can perform downstream tasks in a zero-shot fashion, given natural language prompts that specify the desired behavior. |
| Approach: | They propose a human readable prompt tuning method that incorporates a fluency constraint to find a distribution of effective and fluent prompts. |
| Outcome: | The proposed method outperforms baselines by 7.0% across three tasks. |
Misalignment Attack on Text-to-Image Models via Text Embedding Optimization and Inversion (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Text embedding is a key component of modern NLP models but also poses additional risks. |
| Approach: | They propose a framework that optimizes embeddings and inverts them to obtain misaligned prompts. |
| Outcome: | The proposed framework exploits the continuity and distribution characteristics of text embeddings to obtain misaligned prompts of discrete tokens. |
NormXLogit: The Head-on-Top Never Lies (2025.emnlp-main)
Copied to clipboard
| Challenge: | NormXLogit is a novel approach for assessing the significance of input tokens based on word embeddings . |
| Approach: | They propose a novel method for assessing the significance of input tokens based on the input and output representations associated with each token. |
| Outcome: | The proposed method outperforms gradient-based methods in faithfulness and offers competitive performance compared to leading architecture-specific techniques. |