paper-with-me

홈 › Papers

LM-Polygraph: Uncertainty Estimation for Language Models

2023-11-13 · Ekaterina Fadeeva, Roman Vashurin, Akim Tsvigun, Artem Vazhentsev, Sergey Petrakov, Kirill Fedyanin, Daniil Vasilev, Elizaveta Goncharova, Alexander Panchenko, Maxim Panov, Timothy Baldwin, Artem Shelmanov

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.

📄 PDF Abstract BibTeX arXiv:2311.07383

Code (0)

등록된 구현이 없습니다.

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Adam 설명 없음

Similar Papers 제목 키워드 기반

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

2024-06-21 · Roman Vashurin, Ekaterina Fadeeva, Artem Vazhentsev, Lyudmila Rvanova 외

The rapid proliferation of large language models (LLMs) has stimulated researchers to seek effective and efficient approaches to deal with LLM hallucinations and low-quality outputs. Uncertainty quantification (UQ) is a …

BenchmarkingText GenerationUncertainty Quantification

Real-time Mode-Aware Dataflow: A Dataflow Model to Specify and Analyze Mode-dependent CPSs under Relaxed Timing Constraints

2025-01-13 · Guillaume Roumage, Selma Azaiez, Cyril Faure, Stéphane Louise

Modern Cyber-Physical Systems (CPS) often exhibit both relaxed real-time constraints and a mode-dependent execution. Relaxed real-time constraints mean that only a subset of the processes of a CPS have real-time constrai…

Ingenuity

POLygraph: Polish Fake News Dataset

2024-07-01 · Daniel Dzienisiewicz, Filip Graliński, Piotr Jabłoński, Marek Kubis 외

This paper presents the POLygraph dataset, a unique resource for fake news detection in Polish. The dataset, created by an interdisciplinary team, is composed of two parts: the "fake-or-not" dataset with 11,360 pairs of …

ArticlesFact CheckingFake News Detection

PolyGraph Discrepancy: a classifier-based metric for graph generation

2025-10-07 · Markus Krimmel, Philip Hartout, Karsten Borgwardt, Dexiong Chen arxiv

Existing methods for evaluating graph generative models primarily rely on Maximum Mean Discrepancy (MMD) metrics based on graph descriptors. While these metrics can rank generative models, they do not provide an absolute…

Graph Generation

Syntactic Polygraphs. A Formalism Extending Both Constituency and Dependency

2015-07-01 · WS 2015 7 · Sylvain Kahane, Nicolas Mazziotta