Unexpected Phenomenon: LLMs’ Spurious Associations in Information Extraction (2024.findings-acl)
Copied to clipboard
Weiyan Zhang, Wanpeng Lu, Jiacheng Wang, Yating Wang, Lihan Chen, Haiyun Jiang, Jingping Liu, Tong Ruan
| Challenge: | Information extraction (IE) tasks require a limited number of example instructions to achieve effective performance. |
| Approach: | They propose two strategies to find spurious associations in large language models (LLMs) they use forward label extension and backward label validation to leverage extended labels to improve model performance. |
| Outcome: | The proposed methods improve performance on Chinese and English datasets and 9.55%, 11.42%, and 21.27% in F1 scores on SciERC, ACE05, and DuEE datasets. |
Similar Papers
Conservative Bias in Large Language Models: Measuring Relation Predictions (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) exhibit pronounced conservative bias in relation extraction tasks, often defaulting to no_relation label when an appropriate option is unavailable. |
| Approach: | They systematically evaluate the trade-off between conservative bias and hallucination in relation extraction tasks by using SBERT and LLM prompts to quantify this effect. |
| Outcome: | The proposed model defaults to no_relation label twice as often as hallucination, resulting in significant information loss when reasoning is not explicitly included in the output. |
Rethinking the Role of LLMs for Document-level Relation Extraction: a Refiner with Task Distribution and Probability Fusion (2025.naacl-long)
Copied to clipboard
| Challenge: | Document-level relation extraction (DocRE) provides a broad context for extracting relations for entities. |
| Approach: | They propose a method that utilizes LLMs as a refiner and task distribution and probability fusion to refine LLM-based relation extraction methods. |
| Outcome: | The proposed method outperforms existing LLM-based methods without fine-tuning by 25.2% F1. |
Lost in the Distance: Large Language Models Struggle to Capture Long-Distance Relational Knowledge (2025.findings-naacl)
Copied to clipboard
| Challenge: | Recent large language models have demonstrated impressive capabilities in handling long contexts . however, as context length increases, LLMs struggle more with filtering out irrelevant information . |
| Approach: | They propose to use unrelated sentences to capture relational knowledge over long contexts . they find that LLMs can handle edge noise with little impact, but can reason about distant relationships . |
| Outcome: | The proposed model can handle edge noise with little impact, but its ability to reason about distant relationships declines as the noise grows. |
Stubborn Lexical Bias in Data and Models (2023.findings-acl)
Copied to clipboard
| Challenge: | Recent work has focused on spurious correlations between features and labels in training data . but, we find strong evidence of corresponding bias in the trained models . |
| Approach: | They propose a method to reduce spurious correlations in training data by reweighting it using a large pool of extracted features. |
| Outcome: | The proposed method reduces spurious correlations in training data, but still finds strong evidence of bias in trained models. |
Are LLMs Good Annotators for Discourse-level Event Relation Extraction? (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) have demonstrated proficiency in a wide array of natural language processing tasks, but their effectiveness over discourse-level event relation extraction tasks remains unexplored. |
| Approach: | They evaluate LLMs' ability to address discourse-level event relation extraction tasks using an open-source model and a commercial model. |
| Outcome: | The proposed model performs poorly on discourse-level event relation extraction tasks. |
LLM4RE: A Data-centric Feasibility Study for Relation Extraction (2025.coling-main)
Copied to clipboard
| Challenge: | Relation Extraction (RE) is a critical step in information extraction due to its wide-scale applicability for downstream applications such as Knowledge Base creation and Question Answering (QA). |
| Approach: | They propose to conduct the first feasibility analysis to explore the viability of Large Language Models for RE by investigating their robustness to various RE scenarios stemming from data-specific characteristics. |
| Outcome: | The proposed models are robust to various RE scenarios stemming from data-specific characteristics, but their performance is not yet fully understood. |
Informativeness and Invariance: Two Perspectives on Spurious Correlations in Natural Language (2022.naacl-main)
Copied to clipboard
| Challenge: | Spurious correlations are a threat to the trustworthiness of natural language processing systems. |
| Approach: | They propose a definition of spurious correlations in terms of conditional probabilities and a generalized definition of the term . they propose UIs that allow individual input features to be independent of labels. |
| Outcome: | The proposed definition can be generalized from uniformity to independence without affecting the claims of the paper. |
Quantifying Association Capabilities of Large Language Models and Its Implications on Privacy Leakage (2024.findings-eacl)
Copied to clipboard
| Challenge: | a new study examines the association capabilities of large language models . as models scale up, their ability to associate entities/information intensifies . however, there is a performance gap when associating commonsense knowledge versus PII, with the latter showing lower accuracy. |
| Approach: | They examine the association capabilities of large language models and identify factors that influence their proficiency in associating information. |
| Outcome: | The proposed models show a performance gap when associating commonsense knowledge versus PII, with the latter showing lower accuracy. |
Do LLMs Adhere to Label Definitions? Examining Their Receptivity to External Label Definitions (2025.emnlp-main)
Copied to clipboard
Seyedali Mohammadi, Bhaskara Hanuma Vedula, Hemank Lamba, Edward Raff, Ponnurangam Kumaraguru, Francis Ferraro, Manas Gaur
| Challenge: | Exact label definitions are considered as clues to disambiguate unclear labels, helping models perform their tasks more effectively. |
| Approach: | They conducted controlled experiments on multiple explanation benchmark datasets and label definition conditions using expert-curated, LLM-generated, perturbed, and swapped definitions. |
| Outcome: | The results suggest that models often default to internal representations, particularly in general tasks, while domain-specific tasks benefit more from explicit definitions. |
Spurious Correlations and Beyond: Understanding and Mitigating Shortcut Learning in SDOH Extraction with Large Language Models (2025.acl-short)
Copied to clipboard
| Challenge: | Large language models (LLMs) rely on superficial cues leading to spurious predictions . recent work has highlighted how LLMs exploit spurious patterns rather than learning causal, generalizable features. |
| Approach: | They use a social history annotation corpus dataset to examine drug status extraction . they evaluate prompt engineering and chain-of-thought reasoning to reduce false positives . |
| Outcome: | The proposed model can predict drug use when alcohol or smoking is not present, while uncovering gender disparities in model performance. |