paper-with-me

홈 › Papers

Integrative Decoding: Improve Factuality via Implicit Self-consistency

2024-10-02 · Yi Cheng, Xiao Liang, Yeyun Gong, Wen Xiao, Song Wang, Yuji Zhang, Wenjun Hou, Kaishuai Xu, Wenge Liu, Wenjie Li, Jian Jiao, Qi Chen, Peng Cheng, Wayne Xiong

Self-consistency-based approaches, which involve repeatedly sampling multiple outputs and selecting the most consistent one as the final response, prove to be remarkably effective in improving the factual accuracy of large language models. Nonetheless, existing methods usually have strict constraints on the task format, largely limiting their applicability. In this paper, we present Integrative Decoding (ID), to unlock the potential of self-consistency in open-ended generation tasks. ID operates by constructing a set of inputs, each prepended with a previously sampled response, and then processes them concurrently, with the next token being selected by aggregating of all their corresponding predictions at each decoding step. In essence, this simple approach implicitly incorporates self-consistency in the decoding objective. Extensive evaluation shows that ID consistently enhances factuality over a wide range of language models, with substantial improvements on the TruthfulQA (+11.2%), Biographies (+15.4%) and LongFact (+8.5%) benchmarks. The performance gains amplify progressively as the number of sampled responses increases, indicating the potential of ID to scale up with repeated sampling.

📄 PDF Abstract BibTeX arXiv:2410.01556

Code (1)

yicheng98/integrativedecoding 공식 구현 pytorch

Tasks

TruthfulQA

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality

2025-09-20 · Byeongho Yu, Changhun Lee, Jungyu Jin, Eunhyeok Park arxiv

To mitigate the hallucination problem in large language models, DoLa exploits early exit logits from the same model as a contrastive prior. However, we found that these early exit logits tend to be flat, low in magnitude…

Temporally Consistent Factuality Probing for Large Language Models

2024-09-21 · Ashutosh Bajpai, Aaryan Goyal, Atif Anwer, Tanmoy Chakraborty

The prolific use of Large Language Models (LLMs) as an alternate knowledge base requires them to be factually consistent, necessitating both correctness and consistency traits for paraphrased queries. Recently, significa…

Enhancing Language Model Factuality via Activation-Based Confidence Calibration and Guided Decoding

2024-06-19 · Xin Liu, Farima Fatahi Bayat, Lu Wang

Calibrating language models (LMs) aligns their generation confidence with the actual likelihood of answer correctness, which can inform users about LMs' reliability and mitigate hallucinated content. However, prior calib…

Language ModelingLanguage ModellingTruthfulQA

Only Say What You Know: Calibration-Aware Generation for Long-Form Factuality

2026-05-03 · Wen Luo, Guangyue Peng, Liang Wang, Nan Yang 외 arxiv

Large Reasoning Models achieve strong performance on complex tasks but remain prone to hallucinations, particularly in long-form generation where errors compound across reasoning steps. Existing approaches to improving f…

REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy

2024-06-11 · Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna 외

Decoding methods for large language models (LLMs) usually struggle with the tradeoff between ensuring factuality and maintaining diversity. For example, a higher p threshold in the nucleus (top-p) sampling increases the …

DiversityHallucination