Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators (2024.acl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) tend to be unreliable on fact-based answers. |
| Approach: | They propose a framework for comparing LLMs' confidence over fact-based answers with hidden-state probes that are more reliable than hidden-status probes. |
| Outcome: | The proposed methods show that hidden-state probes provide the most reliable confidence estimates despite requiring access to weights and supervision data. |
Similar Papers
A Survey of Confidence Estimation and Calibration in Large Language Models (2024.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated impressive capabilities across a wide range of tasks in various domains, but they can be unreliable due to factual errors in their generations. |
| Approach: | They summarize recent advances in LLM confidence estimation and calibration and outline their main lessons learned. |
| Outcome: | The proposed methods can be used to assess the reliability of models and to calibrate them across tasks. |
Assessing Factual Reliability of Large Language Model Knowledge (2024.naacl-long)
Copied to clipboard
| Challenge: | Factual knowledge of LLMs is typically evaluated using accuracy, yet this metric does not capture the vulnerability of LRMs to hallucination-inducing factors like prompt and context variability. |
| Approach: | They propose a metric designed to measure LLMs’ factual reliability by comparing the distance between the probability distributions of a valid output and its counterparts produced by the same LLM probing the same fact using different styles of prompts and contexts. |
| Outcome: | The proposed metric measures the distance between the probability distributions of a valid output and its counterparts produced by the same LLM probing the same fact using different styles of prompts and contexts. |
A Survey of Uncertainty Estimation Methods on Large Language Models (2025.findings-acl)
Copied to clipboard
| Challenge: | Large language models (LLMs) have demonstrated remarkable capabilities but could produce biased, hallucinated, or non-factual responses. |
| Approach: | They propose to conduct extensive experimental evaluations of LLM uncertainty estimation methods . large language models have demonstrated remarkable capabilities across tasks . |
| Outcome: | The proposed method could produce biased, hallucinated, or non-factual responses . a lack of comprehensive surveys on LLM uncertainty estimation is a problem . |
Factuality of Large Language Models: A Survey (2024.emnlp-main)
Copied to clipboard
Yuxia Wang, Minghan Wang, Muhammad Arslan Manzoor, Fei Liu, Georgi Georgiev, Rocktim Das, Preslav Nakov
| Challenge: | Large language models (LLMs) are factually incorrect, which limits their applicability in real-world scenarios. |
| Approach: | They analyze existing work to identify major challenges and their associated causes . they propose to evaluate LLMs using a variety of measures to mitigate factual errors . |
| Outcome: | The proposed methods are based on a variety of datasets and proposed strategies to mitigate factual errors. |
FactEval: Evaluating the Robustness of Fact Verification Systems in the Era of Large Language Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) have made significant advances in every natural language processing task, but they are vulnerable to small perturbations in the inputs, raising concerns about their robustness in the real world. |
| Approach: | They propose a large-scale benchmark for extensive evaluation of LLMs in the fact verification domain covering 17 realistic word-level and character-level perturbations and 4 types of subpopulations. |
| Outcome: | The proposed model is brittle to small input changes and exhibits performance variations across different subpopulations. |
On the Calibration of Large Language Models and Alignment (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Large language models are becoming more popular and are proving to be reliable . however, their reliability is often understudied due to their uncertainty and complex structure . |
| Approach: | They conduct a systematic examination of the calibration of aligned language models throughout the entire construction process including pretraining and alignment training. |
| Outcome: | The results shed light on whether popular large language models are well-calibrated and how the training process influences model calibration. |
SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models (2025.naacl-industry)
Copied to clipboard
| Challenge: | Typical evaluations of Large Language Models (LLMs) report a single accuracy metric per dataset, often derived from an optimized setup. |
| Approach: | They propose a framework for non-adversarial evaluation of large language models that evaluates models by repeatedly testing them on the same benchmarks in various setups. |
| Outcome: | The proposed framework evaluates models by repeatedly testing them on the same benchmarks in various setups to give a realistic estimate of their accuracy and consistency. |
Large Language Models Help Humans Verify Truthfulness – Except When They Are Convincingly Wrong (2024.naacl-long)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are increasingly used for accessing information on the web. |
| Approach: | They conduct experiments with 80 crowdworkers to compare LLMs with search engines . they ask LLM to provide contrastive information to reduce over-reliance on LLM . |
| Outcome: | The results show that LLMs can outperform search engines but not LLM explanations . the study shows that LMS explanations are not reliable replacements for reading retrieved passages compared to search engines alone. |
Revisiting Epistemic Markers in Confidence Estimation: Can Markers Accurately Reflect Large Language Models’ Uncertainty? (2025.acl-short)
Copied to clipboard
| Challenge: | Large language models (LLMs) are increasingly used in high-stakes domains, but their confidence is inconsistent in out-of-distribution scenarios. |
| Approach: | They define "marker confidence" as the observed accuracy when a model employs an epistemic marker. |
| Outcome: | The proposed model generalizes well within the same distribution, but its confidence is inconsistent in out-of-distribution scenarios. |
Methods for Estimating and Improving Robustness of Language Models (2022.naacl-srw)
Copied to clipboard
| Challenge: | Large language models suffer from weak generalisation ability due to shallow textual relations over full semantic complexity of the problem. |
| Approach: | They propose to incorporate some of these measures into training objectives to enhance distributional robustness of LLMs. |
| Outcome: | The proposed models outperform human models on complex tasks and outperformed other models on deep networks. |