PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars
- URL: http://arxiv.org/abs/2408.08869v2
- Date: Mon, 19 Aug 2024 04:29:34 GMT
- Title: PEDAL: Enhancing Greedy Decoding with Large Language Models using Diverse Exemplars
- Authors: Sumanth Prabhu,
- Abstract summary: Self-ensembling techniques with diverse reasoning paths have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs)
We introduce PEDAL, a hybrid self-ensembling approach that combines the strengths of diverse exemplar based prompts and LLM based aggregation to achieve improvement in overall performance.
- Score: 1.450405446885067
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Self-ensembling techniques with diverse reasoning paths such as Self-Consistency have demonstrated remarkable performance gains in text generation with Large Language Models (LLMs). However, such techniques depend on the availability of an accurate answer extraction process to aggregate across multiple outputs. Moreover, they acquire higher inference cost, in comparison to Greedy Decoding, due to generation of relatively higher number of output tokens. Research has shown that the free form text outputs from Self-Consistency can be aggregated reliably using LLMs to produce the final output. Additionally, recent advancements in LLM inference have demonstrated that usage of diverse exemplars in prompts have the ability to induce diversity in the LLM outputs. Such proven techniques can be easily extended to self-ensembling based approaches to achieve enhanced results in text generation. In this paper, we introduce PEDAL (Prompts based on Exemplar Diversity Aggregated using LLMs), a hybrid self-ensembling approach, that combines the strengths of diverse exemplar based prompts and LLM based aggregation to achieve improvement in overall performance. On the publicly available SVAMP and ARC datasets, our experiments reveal that PEDAL can achieve better accuracy than Greedy Decoding based strategies with lower inference cost compared to Self Consistency based approaches.
Related papers
- GEM: Empowering LLM for both Embedding Generation and Language Understanding [11.081595808236239]
We propose Generative Embedding large language Model (GEM) to generate high-quality text embeddings.<n>Our method inserts new special token(s) into a text body, and generates summarization embedding of the text by manipulating the attention mask.<n>Our results indicate that our approach can empower LLMs with state-of-the-art text embedding capabilities while maintaining their original NLP performance.
arXiv Detail & Related papers (2025-06-04T18:02:07Z) - Iterative Self-Incentivization Empowers Large Language Models as Agentic Searchers [74.17516978246152]
Large language models (LLMs) have been widely integrated into information retrieval to advance traditional techniques.<n>We propose EXSEARCH, an agentic search framework, where the LLM learns to retrieve useful information as the reasoning unfolds.<n>Experiments on four knowledge-intensive benchmarks show that EXSEARCH substantially outperforms baselines.
arXiv Detail & Related papers (2025-05-26T15:27:55Z) - IDA-Bench: Evaluating LLMs on Interactive Guided Data Analysis [60.32962597618861]
IDA-Bench is a novel benchmark evaluating large language models in multi-round interactive scenarios.<n>Agent performance is judged by comparing its final numerical output to the human-derived baseline.<n>Even state-of-the-art coding agents (like Claude-3.7-thinking) succeed on 50% of the tasks, highlighting limitations not evident in single-turn tests.
arXiv Detail & Related papers (2025-05-23T09:37:52Z) - Ensemble Learning for Large Language Models in Text and Code Generation: A Survey [6.041894045506043]
We focus on four methods and models that show strong performance and potential for broader applications.
These include better representation of diversity, improved output quality, and greater flexibility in applications.
arXiv Detail & Related papers (2025-03-13T18:50:57Z) - Improving Consistency in Large Language Models through Chain of Guidance [9.040736633675136]
Chain of Guidance (CoG) is a multistep prompting technique that generates highly consistent outputs from Large Language Models (LLMs)
We use synthetic data sets comprised of consistent input-output pairs to fine-tune LLMs to produce consistent and correct outputs.
Our fine-tuned models are more than twice as consistent compared to base models and show strong generalization capabilities by producing consistent outputs over datasets not used in the fine-tuning process.
arXiv Detail & Related papers (2025-02-21T20:41:37Z) - M-Ped: Multi-Prompt Ensemble Decoding for Large Language Models [12.96619003056978]
This paper presents a novel multi-prompt ensemble decoding approach designed to bolster the generation quality of Large Language Models.
Given a unique input $X$, we submit $n$ variations of prompts with $X$ to LLMs in batch mode to decode and derive probability distributions.
For each token prediction, we calculate the ensemble probability by averaging the $n$ probability distributions within the batch, utilizing this aggregated probability to generate the token.
arXiv Detail & Related papers (2024-12-24T09:06:58Z) - Balancing Diversity and Risk in LLM Sampling: How to Select Your Method and Parameter for Open-Ended Text Generation [60.493180081319785]
We propose a systematic way to estimate the intrinsic capacity of a truncation sampling method by considering the trade-off between diversity and risk at each decoding step.
Our work provides a comprehensive comparison between existing truncation sampling methods, as well as their recommended parameters as a guideline for users.
arXiv Detail & Related papers (2024-08-24T14:14:32Z) - SELF-GUIDE: Better Task-Specific Instruction Following via Self-Synthetic Finetuning [70.21358720599821]
Large language models (LLMs) hold the promise of solving diverse tasks when provided with appropriate natural language prompts.
We propose SELF-GUIDE, a multi-stage mechanism in which we synthesize task-specific input-output pairs from the student LLM.
We report an absolute improvement of approximately 15% for classification tasks and 18% for generation tasks in the benchmark's metrics.
arXiv Detail & Related papers (2024-07-16T04:41:58Z) - DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph [70.79413606968814]
We introduce Dynamic Evaluation of LLMs via Adaptive Reasoning Graph Evolvement (DARG) to dynamically extend current benchmarks with controlled complexity and diversity.
Specifically, we first extract the reasoning graphs of data points in current benchmarks and then perturb the reasoning graphs to generate novel testing data.
Such newly generated test samples can have different levels of complexity while maintaining linguistic diversity similar to the original benchmarks.
arXiv Detail & Related papers (2024-06-25T04:27:53Z) - Set-Based Prompting: Provably Solving the Language Model Order Dependency Problem [18.020492646988746]
We present Set-Based Prompting, a technique that guarantees the output of an LLM will not have order dependence on a specified set of sub-sequences.
Despite our inputs being out of distribution, the impact on expected accuracy is small, where the expectation is over the order of uniformly chosen shuffling of the candidate responses.
arXiv Detail & Related papers (2024-06-04T16:09:13Z) - One Token Can Help! Learning Scalable and Pluggable Virtual Tokens for Retrieval-Augmented Large Language Models [67.49462724595445]
Retrieval-augmented generation (RAG) is a promising way to improve large language models (LLMs)
We propose a novel method that involves learning scalable and pluggable virtual tokens for RAG.
arXiv Detail & Related papers (2024-05-30T03:44:54Z) - Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration [39.35476224845088]
Large language models (LLMs) exhibit complementary strengths in various tasks, motivating the research of LLM ensembling.
We propose a training-free ensemble framework DeePEn, fusing the informative probability distributions yielded by different LLMs at each decoding step.
arXiv Detail & Related papers (2024-04-19T08:52:22Z) - Bridging the Gap between Different Vocabularies for LLM Ensemble [10.669552498083709]
vocabulary discrepancies among various large language models (LLMs) have constrained previous studies.
We propose a novel method to Ensemble LLMs via Vocabulary Alignment (EVA)
EVA bridges the lexical gap among various LLMs, enabling meticulous ensemble at each generation step.
arXiv Detail & Related papers (2024-04-15T06:28:20Z) - LLM-augmented Preference Learning from Natural Language [19.700169351688768]
Large Language Models (LLMs) are equipped to deal with larger context lengths.
LLMs can consistently outperform the SotA when the target text is large.
Few-shot learning yields better performance than zero-shot learning.
arXiv Detail & Related papers (2023-10-12T17:17:27Z) - From Quantity to Quality: Boosting LLM Performance with Self-Guided Data Selection for Instruction Tuning [52.257422715393574]
We introduce a self-guided methodology for Large Language Models (LLMs) to autonomously discern and select cherry samples from open-source datasets.
Our key innovation, the Instruction-Following Difficulty (IFD) metric, emerges as a pivotal metric to identify discrepancies between a model's expected responses and its intrinsic generation capability.
arXiv Detail & Related papers (2023-08-23T09:45:29Z) - LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and
Generative Fusion [33.73671362609599]
Our framework consists of two modules: PairRanker and GenFuser.
PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs.
GenFuser aims to merge the top-ranked candidates, generating an improved output.
arXiv Detail & Related papers (2023-06-05T03:32:26Z) - OverPrompt: Enhancing ChatGPT through Efficient In-Context Learning [49.38867353135258]
We propose OverPrompt, leveraging the in-context learning capability of LLMs to handle multiple task inputs.
Our experiments show that OverPrompt can achieve cost-efficient zero-shot classification without causing significant detriment to task performance.
arXiv Detail & Related papers (2023-05-24T10:08:04Z)
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.