Challenge: Large language models (LLMs) are difficult to interpret due to their black-box nature and randomness.
Approach: They propose a new method which enhances influence functions by addressing fitting errors by eliminating knowledge bias present in the base model before fine-tuning.
Outcome: The proposed method outperforms existing methods and achieves an average AUC of 91.64%.

Similar Papers

Guide the Learner: Controlling Product of Experts Debiasing Method Based on Token Attribution Similarities (2023.eacl-main)

Copied to clipboard

Challenge: Several proposals have been put forward for improving out-of-distribution performance by mitigating dataset biases.
Approach: They propose a fine-tuning strategy that incorporates the similarity between the main and biased model attribution scores in a Product of Experts (PoE) loss function to further improve OOD performance.
Outcome: The proposed method improves OOD performance while maintaining in-distribution performance.
Debiasing Large Language Models with Structured Knowledge (2024.findings-acl)

Copied to clipboard

Challenge: Existing methods to reduce biases in pre-training models are hampered by their performance.
Approach: They propose a method that utilizes structured knowledge to mitigate bias in LLMs . their method obviates the need for training from scratch, thus offering enhanced scalability .
Outcome: The proposed method outperforms state-of-the-art (SOTA) baselines in the debiasing ability.
Token-wise Influential Training Data Retrieval for Large Language Models (2024.acl-long)

Copied to clipboard

Challenge: Large language models (LLMs) have been widely used in various industries due to their unprecedented scale and impressive capabilities derived from the massive training dataset.
Approach: They propose a framework that can estimate the influence of training data by caching and retrieval.
Outcome: The proposed framework can estimate the influence of training data within minutes, achieving over a speedup of 6,326x.
Automatic Evaluation of Attribution by Large Language Models (2023.findings-emnlp)

Copied to clipboard

Challenge: Generative large language models (LLMs) incorporate external references to generate and support claims. however, evaluating the attribution remains an open problem.
Approach: They investigate automatic evaluation of attribution given by large language models . they define different types of attributed errors and then explore two approaches .
Outcome: The proposed methods highlight promising signals and challenges.
WASA: WAtermark-based Source Attribution for Large Language Model-Generated Data (2025.findings-acl)

Copied to clipboard

Challenge: Large language models (LLMs) have impressive performance but intellectual property concerns are looming . a framework that can be used to perform source attribution for LLMs can be developed.
Approach: They propose a framework that enables an LLM to generate synthetic texts with embedded watermarks that contain information about their source.
Outcome: The proposed framework achieves source attribution accuracy and robustness against adversaries.
Influence Tuning: Demoting Spurious Correlations via Instance Attribution and Instance-Driven Updates (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to interpret black-box models to learn spurious correlations are not well understood.
Approach: They propose a procedure that leverages model interpretations to update parameters towards a plausible interpretation rather than an interpretation that relies on spurious patterns in data.
Outcome: The proposed procedure outperforms baseline methods that use adversarial training in a controlled setup.
Diagnosing Failures in Large Language Models’ Answers: Integrating Error Attribution into Evaluation Framework (2025.findings-acl)

Copied to clipboard

Challenge: Existing evaluation models lack error attribution capability due to their proprietary nature.
Approach: They propose a misattribution framework with 6 primary and 15 secondary categories to facilitate in-depth analysis.
Outcome: The proposed framework is based on a dataset specifically designed for error attribution, along with the corresponding scores and feedback.
Advancing Large Language Model Attribution through Self-Improving (2024.emnlp-main)

Copied to clipboard

Challenge: Teaching large language models to generate text with citations to evidence sources requires high-quality attribution data, which is costly and labor-intensive.
Approach: They propose a framework for iteratively improving the attribution capability of large language models (LLMs) by attributing output to verifiable sources.
Outcome: Experiments on three open-domain question-answering datasets show that START improves in aggregating information across multiple sources.
Matching Pairs: Attributing Fine-Tuned Models to their Pre-Trained Large Language Models (2023.acl-long)

Copied to clipboard

Challenge: generative large language models (LLMs) are widely used but fine-tuned to improve performance on downstream applications leads to violations of model licenses, model theft, and copyright infringement.
Approach: They propose to trace back the origin of a model trained to its pre-trained base model . they use different knowledge levels and attribution strategies to find out how the model was trained .
Outcome: The proposed method can trace back 8 out of 10 fine tuned models with different knowledge levels and attribution strategies.
Attribute or Abstain: Large Language Models as Long Document Assistants (2024.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to attribution have only been evaluated in RAG settings, where initial retrieval confounds performance.
Approach: They propose to use a benchmark to evaluate attribution on long document tasks . they find that citations and additional retrieval perform best for large models .
Outcome: The proposed approach performs best on large and fine-tuned models, while additional retrieval can help for small, prompted models.

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