Bridging the Gap between Different Vocabularies for LLM Ensemble
- URL: http://arxiv.org/abs/2404.09492v1
- Date: Mon, 15 Apr 2024 06:28:20 GMT
- Title: Bridging the Gap between Different Vocabularies for LLM Ensemble
- Authors: Yangyifan Xu, Jinliang Lu, Jiajun Zhang,
- Abstract summary: 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.
- Score: 10.669552498083709
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Ensembling different large language models (LLMs) to unleash their complementary potential and harness their individual strengths is highly valuable. Nevertheless, vocabulary discrepancies among various LLMs have constrained previous studies to either selecting or blending completely generated outputs. This limitation hinders the dynamic correction and enhancement of outputs during the generation process, resulting in a limited capacity for effective ensemble. To address this issue, 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. Specifically, we first learn mappings between the vocabularies of different LLMs with the assistance of overlapping tokens. Subsequently, these mappings are employed to project output distributions of LLMs into a unified space, facilitating a fine-grained ensemble. Finally, we design a filtering strategy to exclude models that generate unfaithful tokens. Experimental results on commonsense reasoning, arithmetic reasoning, machine translation, and data-to-text generation tasks demonstrate the superiority of our approach compared with individual LLMs and previous ensemble methods conducted on complete outputs. Further analyses confirm that our approach can leverage knowledge from different language models and yield consistent improvement.
Related papers
- 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) - Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing [56.75702900542643]
We introduce AlphaLLM for the self-improvements of Large Language Models.
It integrates Monte Carlo Tree Search (MCTS) with LLMs to establish a self-improving loop.
Our experimental results show that AlphaLLM significantly enhances the performance of LLMs without additional annotations.
arXiv Detail & Related papers (2024-04-18T15:21:34Z) - FAC$^2$E: Better Understanding Large Language Model Capabilities by
Dissociating Language and Cognition [57.747888532651]
Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks.
We present FAC$2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
arXiv Detail & Related papers (2024-02-29T21:05:37Z) - Knowledge Fusion of Large Language Models [73.28202188100646]
This paper introduces the notion of knowledge fusion for large language models (LLMs)
We externalize their collective knowledge and unique strengths, thereby elevating the capabilities of the target model beyond those of any individual source LLM.
Our findings confirm that the fusion of LLMs can improve the performance of the target model across a range of capabilities such as reasoning, commonsense, and code generation.
arXiv Detail & Related papers (2024-01-19T05:02:46Z) - Boosting Large Language Model for Speech Synthesis: An Empirical Study [86.89548753080432]
Large language models (LLMs) have made significant advancements in natural language processing and are concurrently extending the language ability to other modalities, such as speech and vision.
We conduct a comprehensive empirical exploration of boosting LLMs with the ability to generate speech, by combining pre-trained LLM LLaMA/OPT and text-to-speech synthesis model VALL-E.
We compare three integration methods between LLMs and speech models, including directly fine-tuned LLMs, superposed layers of LLMs and VALL-E, and coupled LLMs and VALL-E using LLMs as a powerful text encoder
arXiv Detail & Related papers (2023-12-30T14:20:04Z) - Supervised Knowledge Makes Large Language Models Better In-context Learners [94.89301696512776]
Large Language Models (LLMs) exhibit emerging in-context learning abilities through prompt engineering.
The challenge of improving the generalizability and factuality of LLMs in natural language understanding and question answering remains under-explored.
We propose a framework that enhances the reliability of LLMs as it: 1) generalizes out-of-distribution data, 2) elucidates how LLMs benefit from discriminative models, and 3) minimizes hallucinations in generative tasks.
arXiv Detail & Related papers (2023-12-26T07:24:46Z) - Constituency Parsing using LLMs [22.932447078664232]
Constituency parsing is a fundamental yet unsolved natural language processing task.
We employ three linearization strategies to transform output trees into symbol sequences, such that LLMs can solve constituency parsing by generating linearized trees.
Our findings reveal insights into LLMs' performance, generalization abilities, and challenges in constituency parsing.
arXiv Detail & Related papers (2023-10-30T11:39:11Z) - Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue.
By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights.
This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
arXiv Detail & Related papers (2023-10-10T03:06:38Z) - IERL: Interpretable Ensemble Representation Learning -- Combining
CrowdSourced Knowledge and Distributed Semantic Representations [11.008412414253662]
Large Language Models (LLMs) encode meanings of words in the form of distributed semantics.
Recent studies have shown that LLMs tend to generate unintended, inconsistent, or wrong texts as outputs.
We propose a novel ensemble learning method, Interpretable Ensemble Representation Learning (IERL), that systematically combines LLM and crowdsourced knowledge representations.
arXiv Detail & Related papers (2023-06-24T05:02:34Z)
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.