REVIEW 29 cited by
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
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
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
read the original abstract
We present LLM-Blender, an ensembling framework designed to attain consistently superior performance by leveraging the diverse strengths of multiple open-source large language models (LLMs). Our framework consists of two modules: PairRanker and GenFuser, addressing the observation that optimal LLMs for different examples can significantly vary. PairRanker employs a specialized pairwise comparison method to distinguish subtle differences between candidate outputs. It jointly encodes the input text and a pair of candidates, using cross-attention encoders to determine the superior one. Our results demonstrate that PairRanker exhibits the highest correlation with ChatGPT-based ranking. Then, GenFuser aims to merge the top-ranked candidates, generating an improved output by capitalizing on their strengths and mitigating their weaknesses. To facilitate large-scale evaluation, we introduce a benchmark dataset, MixInstruct, which is a mixture of multiple instruction datasets featuring oracle pairwise comparisons. Our LLM-Blender significantly outperform individual LLMs and baseline methods across various metrics, establishing a substantial performance gap.
Forward citations
Cited by 29 Pith papers
-
Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization
Byte-Prefix Marginalization maps a teacher's next-token distribution onto the student's vocabulary through shared byte prefixes plus an explicit residual, giving a mass-preserving target for on-policy distillation acr...
-
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Any single-output LLM ensemble is accuracy-capped at 1-beta where beta is the all-models-wrong rate, a quantity not captured by pairwise correlations and frequently underestimated by copula models.
-
RouteJudge: An Open Platform for Reproducible and Preference-Aware LLM Routing
RouteJudge introduces an open platform for preference-based evaluation of LLM routers via pairwise user comparisons, along with the ORBIT toolbox for standardized routing workflows.
-
Online Pandora's Box for Contextual LLM Cascading
Introduces a parametric reservation-index policy with GMM estimation and UCB exploration for contextual LLM cascading under output-mediated feedback, claiming dimension-dependent square-root regret.
-
Rethinking Predictive Modeling for LLM Routing: When Simple kNN Beats Complex Learned Routers
A well-tuned kNN router matches or exceeds state-of-the-art learned routers on new standardized benchmarks spanning instruction, QA, reasoning, and the first multi-modal visual routing dataset, due to locality of mode...
-
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
Stale-occupancy sequential fine-tuning of multi-agent LLMs incurs an O(n²) certificate penalty; TeamTR resamples under intermediate occupancy and enforces token-level trust regions to restore O(n) scaling and stable gains.
-
Are Diversity Metrics Measuring Diversity? A Capability-Controlled Audit of Majority-Vote Gain in LLM Ensembles
Diversity metrics used to select LLM ensembles are largely capability proxies; after control, only a modest pairwise co-failure association with majority-vote gain remains.
-
Multi-Turn On-Policy Distillation with Prefix Replay
ReOPD offline-distills multi-turn agentic LLMs via teacher-prefix replay plus step-decay sampling, matching online OPD accuracy at ≥4× speed with zero tool calls.
-
SWE-Router: Routing in Multi-turn Agentic Software Engineering Tasks
SWE-Router introduces trajectory-conditioned value-based routing for LLM agents on SWE tasks, with a Bayes-optimality theorem and empirical cost savings while retaining most strong-model performance.
-
Opti-Q: A Constraint-Based Optimization Framework for Multi-LLM Question Planning
Per-question database-style plan search over multi-LLM DAGs improves QA quality under budgets by ~58% (MMLU-Pro) and ~41% (SimpleQA) versus reimplemented baselines.
-
Response Time Enhances Alignment with Heterogeneous Preferences
Response times modeled as drift-diffusion processes enable consistent estimation of population-average preferences from heterogeneous anonymous binary choices.
-
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement l...
-
CADMAS-CTX: Contextual Capability Calibration for Multi-Agent Delegation
CADMAS-CTX replaces static skill profiles with context-conditioned Beta posteriors and uncertainty-penalized routing, yielding higher accuracy on GAIA (0.442) and SWE-bench (31.4%) than static baselines.
-
Privacy-Preserving LLMs Routing
PPRoute achieves plaintext-level LLM routing quality with MPC-based privacy and a 20x speedup over naive encrypted implementations via MPC-friendly encoders, multi-step training, and O(1) communication Top-k search.
-
When Agents Disagree: The Selection Bottleneck in Multi-Agent LLM Pipelines
In a 42-task controlled comparison, selecting the best candidate with judge panels beats MoA-style synthesis in every task, and a crossover threshold explains when team diversity helps.
-
Context Learning for Multi-Agent Discussion
M2CL trains per-agent context generators with a self-adaptive mechanism to maintain coherence and reduce output discrepancies in multi-LLM discussions, yielding 20-50% gains on reasoning, embodied, and mobile control tasks.
-
StatEval: A Comprehensive Benchmark for Large Language Models in Statistics
StatEval is a new 16,000-question statistics benchmark showing that even strong LLMs score below 60% on research-level statistical proof tasks.
-
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Repeated sampling scales problem coverage log-linearly with sample count, improving SWE-bench Lite performance from 15.9% to 56% using 250 samples.
-
RouteLLM: Learning to Route LLMs with Preference Data
Router models trained on preference data dynamically select between strong and weak LLMs, cutting inference costs by more than 2x on benchmarks with no quality loss and showing transfer to new model pairs.
-
Multi-Turn On-Policy Distillation with Prefix Replay
By replaying teacher prefixes with a step-decay schedule, multi-turn on-policy distillation can run without live environment interaction, matching or slightly beating online OPD accuracy.
-
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
A multi-role red-teaming framework with attacker, target, and jury LLMs measures faithfulness in English and Arabic, finding false-premise prompts and length limits change unfaithfulness rates.
-
LRanker: LLM Ranker for Massive Candidates
LRanker combines K-means candidate aggregation with graph-partitioned ensemble of query embeddings to improve LLM ranking accuracy and scalability on massive candidate pools, reporting 3-30% gains on RBench tasks up t...
-
FREE-Switch: Frequency-based Dynamic LoRA Switch for Style Transfer
FREE-Switch dynamically switches LoRA adapters using frequency importance per diffusion step and adds semantic alignment to reduce content drift when merging specialized image generators.
-
Scoring, Reasoning, and Selecting the Best! Ensembling Large Language Models via a Peer-Review Process
LLM-PeerReview ensembles LLMs by scoring responses with LLM-as-Judge and selecting the best via averaging or truth inference, beating Smoothie-Global by 6.9-7.3 points on four datasets.
-
A Scalable Multi-LLM Collaboration System with Retrieval-based Selection and Exploration-Exploitation-Driven Enhancement
SMCS coordinates 15 open-source LLMs via retrieval-based prior selection and exploration-exploitation posterior enhancement, outperforming GPT-4.1 by 5.36% and GPT-o3-mini by 5.28% on eight benchmarks.
-
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
Statistical classifiers built on LLM activation norms and coordinates match or beat trained MLP heads on coarse intent routing and resist camouflage better, while MLPs win on fine-grained subfield distinctions.
-
A Red Teaming Framework for Large Language Models: A Case Study on Faithfulness Evaluation
Introduces a multi-role red teaming framework using attacker and jury models that increases attack success rates by up to 7.9% on LLM faithfulness in question-answering tasks.
-
Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)
HUMBR reduces LLM hallucinations in enterprise workflows by using a hybrid semantic-lexical utility within minimum Bayes risk decoding to identify consensus outputs, with derived error bounds and reported outperforman...
-
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Data-centric filtering yields an 80K preference dataset and reward models that lead RewardBench while boosting other top entries.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.