Papers with model reliability
Evaluating the Robustness of Neural Language Models to Input Perturbations (2021.emnlp-main)
Copied to clipboard
| Challenge: | High-performance neural language models have achieved state-of-the-art results on a wide range of NLP tasks, but results for common benchmark datasets often do not reflect model reliability and robustness when applied to noisy, real-world data. |
| Approach: | They propose to implement character-level and word-level perturbation methods to simulate scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained. |
| Outcome: | The proposed methods simulate scenarios in which input texts may be slightly noisy or different from the data distribution on which NLP systems were trained. |
Navigating the Shortcut Maze: A Comprehensive Analysis of Shortcut Learning in Text Classification by Language Models (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Language models (LMs) often rely on spurious correlations rather than causally relevant features to improve accuracy and generalizability. |
| Approach: | They propose a benchmark that categorizes shortcuts into occurrence, style, and concept . they aim to explore the nuanced ways shortcuts influence the performance of LMs . |
| Outcome: | The proposed benchmark categorizes shortcuts into occurrence, style, and concept . it systematically investigates models’ resilience and susceptibilities to sophisticated shortcuts . |
Extracting Chemical-Protein Interactions via Calibrated Deep Neural Network and Self-training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Several natural language processing methods have been used to extract interactions between chemicals and proteins from biomedical text data. |
| Approach: | They propose a method to extract chemical–protein interactions from biomedical text data . they use a pre-trained language-understanding model and calibration techniques to estimate uncertainty . |
| Outcome: | The proposed approach achieves state-of-the-art performance on the Biocreative VI ChemProt task while preserving higher calibration abilities. |
The Craft of Selective Prediction: Towards Reliable Case Outcome Classification - An Empirical Study on European Court of Human Rights Cases (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing COC tasks prioritize high task performance over model reliability . however, large models exhibit overconfidence and Monte Carlo dropout methods produce reliable confidence estimates . |
| Approach: | They conduct an empirical investigation into how various design choices affect the reliability of COC models within the framework of selective prediction. |
| Outcome: | The proposed model is able to predict the outcome of a legal case based on the text of the case facts and is compared with other models using a pre-training corpus. |
Unveiling Uncertainty: A Deep Dive into Calibration and Performance of Multimodal Large Language Models (2025.coling-main)
Copied to clipboard
| Challenge: | Multimodal large language models combine visual and textual data for tasks like image captioning and visual question answering. |
| Approach: | They propose temperature scaling and iterative prompt optimization to calibrate MLLMs and enhance model reliability. |
| Outcome: | The proposed techniques improve MLLMs and improve model reliability. |
How Many Ratings per Item are Necessary for Reliable Significance Testing? (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing methods for estimating model reliability are based on a few output responses per item. |
| Approach: | They propose a method to determine whether an existing dataset has enough responses per item to assure reliable null hypothesis statistical testing. |
| Outcome: | The proposed method can help researchers make better decisions about how to collect data for AI evaluation. |
RCScore: Quantifying Response Consistency in Large Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Current evaluations of large language models rely on a single instruction template, overlooking models’ sensitivity to instruction style. |
| Approach: | They propose a multi-dimensional framework quantifying how instruction formulation affects model responses by transforming benchmark problems into multiple instruction styles. |
| Outcome: | The proposed framework reveals that instruction style can shift accuracy by 16.7% points. |
Rationales Are Not Silver Bullets: Measuring the Impact of Rationales on Model Performance and Reliability (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing studies have shown that training language models with rationales augmentation is beneficial, but this view does not hold consistently. |
| Approach: | They conduct comprehensive investigations to thoroughly inspect the impact of rationales on model performance and a novel perspective of model reliability. |
| Outcome: | The proposed method outperforms untrained models in several areas and provides informative regulations on the broad utilization of rationales. |
CoME: An Unlearning-based Approach to Conflict-free Model Editing (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) often retain outdated or incorrect information from pre-training, which undermines their reliability. |
| Approach: | They propose a conflict-free model editing framework that selectively removes outdated knowledge from LLMs to improve their accuracy and reliability. |
| Outcome: | The proposed framework improves both editing accuracy and model reliability when applied to existing editing methods. |
UBench: Benchmarking Uncertainty in Large Language Models with Multiple Choice Questions (2025.findings-acl)
Copied to clipboard
Xunzhi Wang, Zhuowei Zhang, Gaonan Chen, Qiongyu Li, Bitong Luo, Zhixin Han, Haotian Wang, Zhiyu Li, Hang Gao, Mengting Hu
| Challenge: | Existing methods for benchmarking the uncertainty of large language models face challenges . existing methods require internal model access, additional training, or high computational costs . |
| Approach: | They propose a new benchmark for evaluating the uncertainty of large language models based on confidence intervals . UBench encompasses 11,978 multiple choice questions spanning knowledge, language, understanding, and reasoning capabilities. |
| Outcome: | The proposed method outperforms existing methods for benchmarking the uncertainty of large language models. |
Sowing the Wind, Reaping the Whirlwind: The Impact of Editing Language Models (2024.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) face challenges in maintaining accuracy due to the dynamic nature of world knowledge. |
| Approach: | They propose to use a benchmark dataset to investigate the effects of model edits on model safety metrics and guardrails. |
| Outcome: | The proposed dataset sheds light on how the edits, impact the model’s safety metrics and guardrails. |
Echoes of Agreement: Argument Driven Sycophancy in Large Language models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Existing evaluations of political biases in Large Language Models outline the high sensitivity to prompt formulation. |
| Approach: | They investigate how argumentative prompts induce sycophantic behaviour in Large Language Models in a political context. |
| Outcome: | The proposed model sycophancy is observed in single and multi-turn interactions and its intensity correlates with argument strength. |
Spotting Out-of-Character Behavior: Atomic-Level Evaluation of Persona Fidelity in Open-Ended Generation (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing evaluation methods struggle to capture subtle inconsistencies in large language models. |
| Approach: | They propose an atomic-level evaluation framework that quantifies persona fidelity at a finer granularity. |
| Outcome: | The proposed framework detects inconsistencies that prior evaluation methods overlook . it captures subtle deviations that real users would encounter . |
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions (2025.emnlp-main)
Copied to clipboard
| Challenge: | Large language models (LLMs) often generate confident yet inaccurate responses, introducing significant risks for deployment in safety-critical domains. |
| Approach: | They propose a method to detect model hallucination by systematic analysis of information flow across model layers. |
| Outcome: | The proposed approach improves model reliability by immediately integrating with universal LLMs without additional training or architectural modifications. |
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say “I Don’t Know” (2026.findings-acl)
Copied to clipboard
| Challenge: | Large language models struggle to recognize their knowledge limits in closed-book question answering . disagreements between prompting regimes are indicative of potential errors, study finds . |
| Approach: | They evaluate three task-equivalent prompting regimes: Direct, Assistive, Incremental . disagreements between prompting régimes provide a precise signal of internal uncertainty . |
| Outcome: | The proposed decomposed prompting outperforms standard uncertainty baselines as an error detector. |