Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraph

Uncertainty quantification (UQ) is becoming increasingly recognized as a critical component of applications that rely on machine learning (ML). The rapid proliferation of large language models (LLMs) has stimulated researchers to seek efficient and effective approaches to UQ in text generation tasks, as in addition to their emerging capabilities, these models have introduced new challenges for building safe applications. As with other ML models, LLMs are prone to make incorrect predictions, ``hallucinate'' by fabricating claims, or simply generate low-quality output for a given input. UQ is a key element in dealing with these challenges. However research to date on UQ methods for LLMs has been fragmented, with disparate evaluation methods. In this work, we tackle this issue by introducing a novel benchmark that implements a collection of state-of-the-art UQ baselines, and provides an environment for controllable and consistent evaluation of novel techniques by researchers in various text generation tasks. Our benchmark also supports the assessment of confidence normalization methods in terms of their ability to provide interpretable scores. Using our benchmark, we conduct a large-scale empirical investigation of UQ and normalization techniques across nine tasks and shed light on the most promising approaches.

Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian

There has been a surge in the development of various Large Language Models (LLMs). However, text generation for languages other than English often faces significant challenges, including poor generation quality and the reduced computational performance due to the disproportionate representation of tokens in model's vocabulary. In this work, we address these issues and introduce Vikhr, a new state-of-the-art open-source instruction-tuned LLM designed specifically for the Russian language. Unlike previous efforts for Russian that utilize computationally inexpensive LoRA adapters on top of English-oriented models, Vikhr features an adapted tokenizer vocabulary and undergoes the continued pre-training and instruction tuning of all weights. This approach not only enhances the model's performance but also significantly improves its computational and contextual efficiency. The remarkable performance of Vikhr across various Russian-language benchmarks can also be attributed to our efforts in expanding instruction datasets and corpora for continued pre-training. Vikhr not only sets the new state of the art among open-source LLMs for Russian, but even outperforms some proprietary closed-source models on certain benchmarks. The model weights, instruction sets, and code are publicly available

SemEval-2024 Task 8: Multidomain, Multimodel and Multilingual Machine-Generated Text Detection

We present the results and the main findings of SemEval-2024 Task 8: Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection. The task featured three subtasks. Subtask A is a binary classification task determining whether a text is written by a human or generated by a machine. This subtask has two tracks: a monolingual track focused solely on English texts and a multilingual track. Subtask B is to detect the exact source of a text, discerning whether it is written by a human or generated by a specific LLM. Subtask C aims to identify the changing point within a text, at which the authorship transitions from human to machine. The task attracted a large number of participants: subtask A monolingual (126), subtask A multilingual (59), subtask B (70), and subtask C (30). In this paper, we present the task, analyze the results, and discuss the system submissions and the methods they used. For all subtasks, the best systems used LLMs.

Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantification

Large language models (LLMs) are notorious for hallucinating, i.e., producing erroneous claims in their output. Such hallucinations can be dangerous, as occasional factual inaccuracies in the generated text might be obscured by the rest of the output being generally factual, making it extremely hard for the users to spot them. Current services that leverage LLMs usually do not provide any means for detecting unreliable generations. Here, we aim to bridge this gap. In particular, we propose a novel fact-checking and hallucination detection pipeline based on token-level uncertainty quantification. Uncertainty scores leverage information encapsulated in the output of a neural network or its layers to detect unreliable predictions, and we show that they can be used to fact-check the atomic claims in the LLM output. Moreover, we present a novel token-level uncertainty quantification method that removes the impact of uncertainty about what claim to generate on the current step and what surface form to use. Our method Claim Conditioned Probability (CCP) measures only the uncertainty of particular claim value expressed by the model. Experiments on the task of biography generation demonstrate strong improvements for CCP compared to the baselines for six different LLMs and three languages. Human evaluation reveals that the fact-checking pipeline based on uncertainty quantification is competitive with a fact-checking tool that leverages external knowledge.

M4GT-Bench: Evaluation Benchmark for Black-Box Machine-Generated Text Detection

The advent of Large Language Models (LLMs) has brought an unprecedented surge in machine-generated text (MGT) across diverse channels. This raises legitimate concerns about its potential misuse and societal implications. The need to identify and differentiate such content from genuine human-generated text is critical in combating disinformation, preserving the integrity of education and scientific fields, and maintaining trust in communication. In this work, we address this problem by introducing a new benchmark involving multilingual, multi-domain and multi-generator for MGT detection -- M4GT-Bench. It is collected for three task formulations: (1) mono-lingual and multi-lingual binary MGT detection; (2) multi-way detection identifies which particular model generates the text; and (3) human-machine mixed text detection, where a word boundary delimiting MGT from human-written content should be determined. Human evaluation for Task 2 shows less than random guess performance, demonstrating the challenges to distinguish unique LLMs. Promising results always occur when training and test data distribute within the same domain or generators.

LM-Polygraph: Uncertainty Estimation for Language Models

Recent advancements in the capabilities of large language models (LLMs) have paved the way for a myriad of groundbreaking applications in various fields. However, a significant challenge arises as these models often "hallucinate", i.e., fabricate facts without providing users an apparent means to discern the veracity of their statements. Uncertainty estimation (UE) methods are one path to safer, more responsible, and more effective use of LLMs. However, to date, research on UE methods for LLMs has been focused primarily on theoretical rather than engineering contributions. In this work, we tackle this issue by introducing LM-Polygraph, a framework with implementations of a battery of state-of-the-art UE methods for LLMs in text generation tasks, with unified program interfaces in Python. Additionally, it introduces an extendable benchmark for consistent evaluation of UE techniques by researchers, and a demo web application that enriches the standard chat dialog with confidence scores, empowering end-users to discern unreliable responses. LM-Polygraph is compatible with the most recent LLMs, including BLOOMz, LLaMA-2, ChatGPT, and GPT-4, and is designed to support future releases of similarly-styled LMs.

M4: Multi-generator, Multi-domain, and Multi-lingual Black-Box Machine-Generated Text Detection

Large language models (LLMs) have demonstrated remarkable capability to generate fluent responses to a wide variety of user queries, but this has also resulted in concerns regarding the potential misuse of such texts in journalism, educational, and academic context. In this work, we aim to develop automatic systems to identify machine-generated text and to detect potential misuse. We first introduce a large-scale benchmark M4, which is multi-generator, multi-domain, and multi-lingual corpus for machine-generated text detection. Using the dataset, we experiment with a number of methods and we show that it is challenging for detectors to generalize well on unseen examples if they are either from different domains or are generated by different large language models. In such cases, detectors tend to misclassify machine-generated text as human-written. These results show that the problem is far from solved and there is a lot of room for improvement. We believe that our dataset M4, which covers different generators, domains and languages, will enable future research towards more robust approaches for this pressing societal problem. The M4 dataset is available at https://github.com/mbzuai-nlp/M4.

Active Learning for Abstractive Text Summarization

Construction of human-curated annotated datasets for abstractive text summarization (ATS) is very time-consuming and expensive because creating each instance requires a human annotator to read a long document and compose a shorter summary that would preserve the key information relayed by the original document. Active Learning (AL) is a technique developed to reduce the amount of annotation required to achieve a certain level of machine learning model performance. In information extraction and text classification, AL can reduce the amount of labor up to multiple times. Despite its potential for aiding expensive annotation, as far as we know, there were no effective AL query strategies for ATS. This stems from the fact that many AL strategies rely on uncertainty estimation, while as we show in our work, uncertain instances are usually noisy, and selecting them can degrade the model performance compared to passive annotation. We address this problem by proposing the first effective query strategy for AL in ATS based on diversity principles. We show that given a certain annotation budget, using our strategy in AL annotation helps to improve the model performance in terms of ROUGE and consistency scores. Additionally, we analyze the effect of self-learning and show that it can further increase the performance of the model.

Medical Image Captioning via Generative Pretrained Transformers

The automatic clinical caption generation problem is referred to as proposed model combining the analysis of frontal chest X-Ray scans with structured patient information from the radiology records. We combine two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The proposed combination of these models generates a textual summary with the essential information about pathologies found, their location, and the 2D heatmaps localizing each pathology on the original X-Ray scans. The proposed model is tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO. The results measured with the natural language assessment metrics prove their efficient applicability to the chest X-Ray image captioning.

NeuralSympCheck: A Symptom Checking and Disease Diagnostic Neural Model with Logic Regularization

The symptom checking systems inquire users for their symptoms and perform a rapid and affordable medical assessment of their condition. The basic symptom checking systems based on Bayesian methods, decision trees, or information gain methods are easy to train and do not require significant computational resources. However, their drawbacks are low relevance of proposed symptoms and insufficient quality of diagnostics. The best results on these tasks are achieved by reinforcement learning models. Their weaknesses are the difficulty of developing and training such systems and limited applicability to cases with large and sparse decision spaces. We propose a new approach based on the supervised learning of neural models with logic regularization that combines the advantages of the different methods. Our experiments on real and synthetic data show that the proposed approach outperforms the best existing methods in the accuracy of diagnosis when the number of diagnoses and symptoms is large.