paper-with-me

Papers

Self-Evaluation Improves Selective Generation in Large Language Models

2023-12-14 · Jie Ren, Yao Zhao, Tu Vu, Peter J. Liu, Balaji Lakshminarayanan

Safe deployment of large language models (LLMs) may benefit from a reliable method for assessing their generated content to determine when to abstain or to selectively generate. While likelihood-based metrics such as perplexity are widely employed, recent research has demonstrated the limitations of using sequence-level probability estimates given by LLMs as reliable indicators of generation quality. Conversely, LLMs have demonstrated strong calibration at the token level, particularly when it comes to choosing correct answers in multiple-choice questions or evaluating true/false statements. In this work, we reformulate open-ended generation tasks into token-level prediction tasks, and leverage LLMs' superior calibration at the token level. We instruct an LLM to self-evaluate its answers, employing either a multi-way comparison or a point-wise evaluation approach, with the option to include a ``None of the above'' option to express the model's uncertainty explicitly. We benchmark a range of scoring methods based on self-evaluation and evaluate their performance in selective generation using TruthfulQA and TL;DR. Through experiments with PaLM-2 and GPT-3, we demonstrate that self-evaluation based scores not only improve accuracy, but also correlate better with the overall quality of generated content.

📄 PDF Abstract BibTeX arXiv:2312.09300

Code (0)

등록된 구현이 없습니다.

Tasks

Multiple-choiceTruthfulQA

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Adam 설명 없음
{Dispute@FaQ-s}How to file a dispute with Expedia? How to file a dispute with Expedia? To file a complaint against Expedia, first try contacting their customer service directly. You can reach them by phone at…
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

Similar Papers 제목 키워드 기반

Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs

2023-10-18 · Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi, Sercan O Arik 외

Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes decision-making scenarios is still limited…

Decision MakingNatural Language UnderstandingPredictionQuestion Answering

Self-training Large Language Models through Knowledge Detection

2024-06-17 · Wei Jie Yeo, Teddy Ferdinan, Przemyslaw Kazienko, Ranjan Satapathy 외

Large language models (LLMs) often necessitate extensive labeled datasets and training compute to achieve impressive performance across downstream tasks. This paper explores a self-training paradigm, where the LLM autono…

HallucinationLanguage ModelingLanguage Modelling

Decoding Memories: An Efficient Pipeline for Self-Consistency Hallucination Detection

2025-08-28 · Weizhi Gao, Xiaorui Liu, Feiyi Wang, Dan Lu 외 arxiv

Large language models (LLMs) have demonstrated impressive performance in both research and real-world applications, but they still struggle with hallucination. Existing hallucination detection methods often perform poorl…

Response Generation

Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation

2026-04-21 · Thomas Zollo, Jimmy Wang, Richard Zemel arxiv

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repe…

Becoming Experienced Judges: Selective Test-Time Learning for Evaluators

2025-12-07 · Seungyeon Jwa, Daechul Ahn, Reokyoung Kim, Dongyeop Kang 외 arxiv

Automatic evaluation with large language models, commonly known as LLM-as-a-judge, is now standard across reasoning and alignment tasks. Despite evaluating many samples in deployment, these evaluators typically (i) treat…