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

• URL: http://arxiv.org/abs/2406.07735v1
• Date: Tue, 11 Jun 2024 21:44:49 GMT
• Title: REAL Sampling: Boosting Factuality and Diversity of Open-Ended Generation via Asymptotic Entropy
• Authors: Haw-Shiuan Chang, Nanyun Peng, Mohit Bansal, Anil Ramakrishna, Tagyoung Chung,
• Abstract summary: Decoding methods for large language models (LLMs) usually struggle with the tradeoff between ensuring factuality and maintaining diversity. We propose REAL sampling, a decoding method that improved factuality and diversity over nucleus sampling.
• Score: 93.8400683020273
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 diversity but decreases the factuality, and vice versa. In this paper, we propose REAL (Residual Entropy from Asymptotic Line) sampling, a decoding method that achieves improved factuality and diversity over nucleus sampling by predicting an adaptive threshold of $p$. Specifically, REAL sampling predicts the step-wise likelihood of an LLM to hallucinate, and lowers the p threshold when an LLM is likely to hallucinate. Otherwise, REAL sampling increases the p threshold to boost the diversity. To predict the step-wise hallucination likelihood without supervision, we construct a Token-level Hallucination Forecasting (THF) model to predict the asymptotic entropy (i.e., inherent uncertainty) of the next token by extrapolating the next-token entropies from a series of LLMs with different sizes. If a LLM's entropy is higher than the asymptotic entropy (i.e., the LLM is more uncertain than it should be), the THF model predicts a high hallucination hazard, which leads to a lower p threshold in REAL sampling. In the FactualityPrompts benchmark, we demonstrate that REAL sampling based on a 70M THF model can substantially improve the factuality and diversity of 7B LLMs simultaneously, judged by both retrieval-based metrics and human evaluation. After combined with contrastive decoding, REAL sampling outperforms 9 sampling methods, and generates texts that are more factual than the greedy sampling and more diverse than the nucleus sampling with $p=0.5$. Furthermore, the predicted asymptotic entropy is also a useful unsupervised signal for hallucination detection tasks.

Related papers

• Unveiling the Statistical Foundations of Chain-of-Thought Prompting Methods [59.779795063072655]
  Chain-of-Thought (CoT) prompting and its variants have gained popularity as effective methods for solving multi-step reasoning problems. We analyze CoT prompting from a statistical estimation perspective, providing a comprehensive characterization of its sample complexity.
  arXiv  Detail & Related papers  (2024-08-25T04:07:18Z)
• Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs [4.122612309805664]
  Large Language Models (LLMs) generate text by sampling the next token from a probability distribution over the vocabulary at each decoding step. We propose min-p sampling, a dynamic truncation method that adjusts the sampling threshold based on the model's confidence by scaling according to the top token's probability. We conduct extensive experiments on benchmarks including GPQA, GSM8K, and AlpacaEval Creative Writing, demonstrating that min-p sampling improves both the quality and diversity of generated text, particularly at high temperatures.
  arXiv  Detail & Related papers  (2024-07-01T08:37:25Z)
• Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs [32.901839335074676]
  Hallucinations present a major challenge to the practical adoption of Large Language Models. Recent work by Farquhar et al. (2024) proposes semantic entropy (SE), which can detect hallucinations by estimating uncertainty in the space semantic meaning for a set of model generations. We propose SEPs, which directly approximate SE from the hidden states of a single generation.
  arXiv  Detail & Related papers  (2024-06-22T19:46:06Z)
• Do LLMs Play Dice? Exploring Probability Distribution Sampling in Large Language Models for Behavioral Simulation [73.58618024960968]
  An increasing number of studies are employing large language models (LLMs) as agents to emulate the sequential decision-making processes of humans. This arouses curiosity regarding the capacity of LLM agents to comprehend probability distributions. Our analysis indicates that LLM agents can understand probabilities, but they struggle with probability sampling.
  arXiv  Detail & Related papers  (2024-04-13T16:59:28Z)
• On Optimal Sampling for Learning SDF Using MLPs Equipped with Positional Encoding [79.67071790034609]
  We devise a tool to determine the appropriate sampling rate for learning an accurate neural implicit field without undesirable side effects. It is observed that a PE-equipped has an intrinsic frequency much higher than the highest frequency component in the PE layer. We empirically show in the setting of SDF fitting, this recommended sampling rate is sufficient to secure accurate fitting results.
  arXiv  Detail & Related papers  (2024-01-02T10:51:52Z)
• Amortizing intractable inference in large language models [56.92471123778389]
  We use amortized Bayesian inference to sample from intractable posterior distributions. We empirically demonstrate that this distribution-matching paradigm of LLM fine-tuning can serve as an effective alternative to maximum-likelihood training. As an important application, we interpret chain-of-thought reasoning as a latent variable modeling problem.
  arXiv  Detail & Related papers  (2023-10-06T16:36:08Z)
• Preconditioned Score-based Generative Models [49.88840603798831]
  An intuitive acceleration method is to reduce the sampling iterations which however causes severe performance degradation. We propose a model-agnostic bfem preconditioned diffusion sampling (PDS) method that leverages matrix preconditioning to alleviate the aforementioned problem. PDS alters the sampling process of a vanilla SGM at marginal extra computation cost, and without model retraining.
  arXiv  Detail & Related papers  (2023-02-13T16:30:53Z)
• Diverse Human Motion Prediction via Gumbel-Softmax Sampling from an Auxiliary Space [34.83587750498361]
  Diverse human motion prediction aims at predicting multiple possible future pose sequences from a sequence of observed poses. Previous approaches usually employ deep generative networks to model the conditional distribution of data, and then randomly sample outcomes from the distribution. We propose a novel sampling strategy for sampling very diverse results from an imbalanced multimodal distribution.
  arXiv  Detail & Related papers  (2022-07-15T09:03:57Z)
• Selectively increasing the diversity of GAN-generated samples [8.980453507536017]
  We propose a novel method to selectively increase the diversity of GAN-generated samples. We show the superiority of our method in a synthetic benchmark as well as a real-life scenario simulating data from the Zero Degree Calorimeter of ALICE experiment in CERN.
  arXiv  Detail & Related papers  (2022-07-04T16:27:06Z)
• DLow: Diversifying Latent Flows for Diverse Human Motion Prediction [32.22704734791378]
  We propose a novel sampling method, Diversifying Latent Flows (DLow), to produce a diverse set of samples from a pretrained deep generative model. During training, DLow uses a diversity-promoting prior over samples as an objective to optimize the latent mappings to improve sample diversity. Our experiments demonstrate that DLow outperforms state-of-the-art baseline methods in terms of sample diversity and accuracy.
  arXiv  Detail & Related papers  (2020-03-18T17:58:11Z)

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.