Concurrent Linguistic Error Detection (CLED) for Large Language Models
- URL: http://arxiv.org/abs/2403.16393v1
- Date: Mon, 25 Mar 2024 03:17:27 GMT
- Title: Concurrent Linguistic Error Detection (CLED) for Large Language Models
- Authors: Jinhua Zhu, Javier Conde, Zhen Gao, Pedro Reviriego, Shanshan Liu, Fabrizio Lombardi,
- Abstract summary: We propose Concurrent Linguistic Error Detection (CLED) for large language models (LLMs)
CLED extracts some linguistic features of the text generated by the LLM and feeds them to a concurrent classifier that detects errors.
The proposed CLED scheme has been evaluated on the T5 model when used for news summarization and on the OPUS-MT model when used for translation.
- Score: 13.01669288397494
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The wide adoption of Large language models (LLMs) makes their dependability a pressing concern. Detection of errors is the first step to mitigating their impact on a system and thus, efficient error detection for LLMs is an important issue. In many settings, the LLM is considered as a black box with no access to the internal nodes; this prevents the use of many error detection schemes that need access to the model's internal nodes. An interesting observation is that the output of LLMs in error-free operation should be valid and normal text. Therefore, when the text is not valid or differs significantly from normal text, it is likely that there is an error. Based on this observation we propose to perform Concurrent Linguistic Error Detection (CLED); this scheme extracts some linguistic features of the text generated by the LLM and feeds them to a concurrent classifier that detects errors. Since the proposed error detection mechanism only relies on the outputs of the model, then it can be used on LLMs in which there is no access to the internal nodes. The proposed CLED scheme has been evaluated on the T5 model when used for news summarization and on the OPUS-MT model when used for translation. In both cases, the same set of linguistic features has been used for error detection to illustrate the applicability of the proposed scheme beyond a specific case. The results show that CLED can detect most of the errors at a low overhead penalty. The use of the concurrent classifier also enables a trade-off between error detection effectiveness and its associated overhead, so providing flexibility to a designer.
Related papers
- Large Language Models for Anomaly Detection in Computational Workflows: from Supervised Fine-Tuning to In-Context Learning [9.601067780210006]
This paper leverages large language models (LLMs) for workflow anomaly detection by exploiting their ability to learn complex data patterns.
Two approaches are investigated: 1) supervised fine-tuning (SFT), where pre-trained LLMs are fine-tuned on labeled data for sentence classification to identify anomalies, and 2) in-context learning (ICL) where prompts containing task descriptions and examples guide LLMs in few-shot anomaly detection without fine-tuning.
arXiv Detail & Related papers (2024-07-24T16:33:04Z) - Rectifier: Code Translation with Corrector via LLMs [11.38401806203093]
We propose a general corrector, namely Rectifier, which is a micro and universal model for repairing translation errors.
The experimental results on translation tasks between C++, Java, and Python show that our model has effective repair ability.
arXiv Detail & Related papers (2024-07-10T08:58:41Z) - Understanding and Mitigating Language Confusion in LLMs [76.96033035093204]
We evaluate 15 typologically diverse languages with existing and newly-created English and multilingual prompts.
We find that Llama Instruct and Mistral models exhibit high degrees of language confusion.
We find that language confusion can be partially mitigated via few-shot prompting, multilingual SFT and preference tuning.
arXiv Detail & Related papers (2024-06-28T17:03:51Z) - Anomaly Detection of Tabular Data Using LLMs [54.470648484612866]
We show that pre-trained large language models (LLMs) are zero-shot batch-level anomaly detectors.
We propose an end-to-end fine-tuning strategy to bring out the potential of LLMs in detecting real anomalies.
arXiv Detail & Related papers (2024-06-24T04:17:03Z) - Detecting Errors through Ensembling Prompts (DEEP): An End-to-End LLM Framework for Detecting Factual Errors [11.07539342949602]
We propose an end-to-end framework for detecting factual errors in text summarization.
Our framework uses a diverse set of LLM prompts to identify factual inconsistencies.
We calibrate the ensembled models to produce empirically accurate probabilities that a text is factually consistent or free of hallucination.
arXiv Detail & Related papers (2024-06-18T18:59:37Z) - Where Do Large Language Models Fail When Generating Code? [10.519984835232359]
Large Language Models (LLMs) have shown great potential in code generation.
It is unclear what kinds of code generation errors LLMs can make.
We analyzed incorrect code snippets generated by six popular LLMs on the HumanEval dataset.
arXiv Detail & Related papers (2024-06-13T01:29:52Z) - Improving Logits-based Detector without Logits from Black-box LLMs [56.234109491884126]
Large Language Models (LLMs) have revolutionized text generation, producing outputs that closely mimic human writing.
We present Distribution-Aligned LLMs Detection (DALD), an innovative framework that redefines the state-of-the-art performance in black-box text detection.
DALD is designed to align the surrogate model's distribution with that of unknown target LLMs, ensuring enhanced detection capability and resilience against rapid model iterations.
arXiv Detail & Related papers (2024-06-07T19:38:05Z) - Knowledge-Augmented Language Model Verification [68.6099592486075]
Recent Language Models (LMs) have shown impressive capabilities in generating texts with the knowledge internalized in parameters.
We propose to verify the output and the knowledge of the knowledge-augmented LMs with a separate verifier.
Our results show that the proposed verifier effectively identifies retrieval and generation errors, allowing LMs to provide more factually correct outputs.
arXiv Detail & Related papers (2023-10-19T15:40:00Z) - Concurrent Classifier Error Detection (CCED) in Large Scale Machine
Learning Systems [10.839595991409828]
We introduce Concurrent Error Detection (CCED), a scheme to implement CED in Machine Learning systems.
CCED identifies a set of check signals in the main ML system and feeds them to the concurrent ML that is trained to detect errors.
Results show that more than 95 percent of the errors are detected when using a simple Random Forest classifier.
arXiv Detail & Related papers (2023-06-02T12:36:05Z) - Rethinking Masked Language Modeling for Chinese Spelling Correction [70.85829000570203]
We study Chinese Spelling Correction (CSC) as a joint decision made by two separate models: a language model and an error model.
We find that fine-tuning BERT tends to over-fit the error model while under-fit the language model, resulting in poor generalization to out-of-distribution error patterns.
We demonstrate that a very simple strategy, randomly masking 20% non-error tokens from the input sequence during fine-tuning is sufficient for learning a much better language model without sacrificing the error model.
arXiv Detail & Related papers (2023-05-28T13:19:12Z) - Towards Fine-Grained Information: Identifying the Type and Location of
Translation Errors [80.22825549235556]
Existing approaches can not synchronously consider error position and type.
We build an FG-TED model to predict the textbf addition and textbfomission errors.
Experiments show that our model can identify both error type and position concurrently, and gives state-of-the-art results.
arXiv Detail & Related papers (2023-02-17T16:20:33Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.