Pith. sign in

REVIEW 3 cited by

Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2404.12715 v2 pith:YIBRVCTC submitted 2024-04-19 cs.CL

classification cs.CL
keywords llmsmodeldeepenprobabilitydifferentdistributionsensembleensembles
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Large language models (LLMs) exhibit complementary strengths in various tasks, motivating the research of LLM ensembling. However, existing work focuses on training an extra reward model or fusion model to select or combine all candidate answers, posing a great challenge to the generalization on unseen data distributions. Besides, prior methods use textual responses as communication media, ignoring the valuable information in the internal representations. In this work, we propose a training-free ensemble framework DeePEn, fusing the informative probability distributions yielded by different LLMs at each decoding step. Unfortunately, the vocabulary discrepancy between heterogeneous LLMs directly makes averaging the distributions unfeasible due to the token misalignment. To address this challenge, DeePEn maps the probability distribution of each model from its own probability space to a universal relative space based on the relative representation theory, and performs aggregation. Next, we devise a search-based inverse transformation to transform the aggregated result back to the probability space of one of the ensembling LLMs (main model), in order to determine the next token. We conduct extensive experiments on ensembles of different number of LLMs, ensembles of LLMs with different architectures, and ensembles between the LLM and the specialist model. Experimental results show that (i) DeePEn achieves consistent improvements across six benchmarks covering subject examination, reasoning, and knowledge, (ii) a well-performing specialist model can benefit from a less effective LLM through distribution fusion, and (iii) DeePEn has complementary strengths with other ensemble methods such as voting.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units

    cs.AI 2025-08 conditional novelty 6.0 of 10

    MCSU-based vocabulary alignment plus distance-based dynamic selection (DDS) lets several LLMs vote token-by-token, beating single models and prior ensemble baselines on multiple reasoning benchmarks without training.

  2. KABB: Knowledge-Aware Bayesian Bandits for Dynamic Expert Coordination in Multi-Agent Systems

    cs.AI 2025-02 reject novelty 5.0 of 10

    A knowledge-aware Bayesian bandit that selects specialist LLM experts per task is reported to beat Mixture-of-Agents on AlpacaEval 2.0 and MT-Bench while using fewer models.

  3. Enhancing Answer Reliability Through Inter-Model Consensus of Large Language Models

    cs.CL 2024-11 reject novelty 3.0 of 10

    A study measures how often GPT-4, Claude, LLaMA, and Gemini agree on PhD-level statistics questions, finding that Claude and GPT-4 produce questions with higher inter-model agreement, but the reliability metric relies...

Pith tools