REVIEW 2 cited by
Bridging the Gap between Different Vocabularies for LLM Ensemble
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
read the original 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.
Forward citations
Cited by 2 Pith papers
-
Dynamic Collaboration of Multi-Language Models based on Minimal Complete Semantic Units
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.
-
One for All: Update Parameterized Knowledge Across Multiple Models
One fine-tuned small model plus an ensemble step can update a fact across multiple large language models with a single edit, outperforming separate per-model editing.
Discussion (0). Continue with ORCID to comment.