The authors create the first large-scale dataset and taxonomy of failure modes in multi-agent LLM systems to explain their limited performance gains.
super hub Mixed citations
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
Mixed citation behavior. Most common role is background (47%).
210
Pith papers citing it
Background
47% of classified citations
abstract
Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-bench, a multi-turn question set; and Chatbot Arena, a crowdsourced battle platform. Our results reveal that strong LLM judges like GPT-4 can match both controlled and crowdsourced human preferences well, achieving over 80% agreement, the same level of agreement between humans. Hence, LLM-as-a-judge is a scalable and explainable way to approximate human preferences, which are otherwise very expensive to obtain. Additionally, we show our benchmark and traditional benchmarks complement each other by evaluating several variants of LLaMA and Vicuna. The MT-bench questions, 3K expert votes, and 30K conversations with human preferences are publicly available at https://github.com/lm-sys/FastChat/tree/main/fastchat/llm_judge.
hub tools
citation-role summary
background 15
method 10
dataset 4
baseline 1
citation-polarity summary
claims ledger
- abstract Evaluating large language model (LLM) based chat assistants is challenging due to their broad capabilities and the inadequacy of existing benchmarks in measuring human preferences. To address this, we explore using strong LLMs as judges to evaluate these models on more open-ended questions. We examine the usage and limitations of LLM-as-a-judge, including position, verbosity, and self-enhancement biases, as well as limited reasoning ability, and propose solutions to mitigate some of them. We then verify the agreement between LLM judges and human preferences by introducing two benchmarks: MT-be
authors
co-cited works
representative citing papers
ORPO performs preference alignment during supervised fine-tuning via a monolithic odds ratio penalty, allowing 7B models to outperform larger state-of-the-art models on alignment benchmarks.
LongBench is the first bilingual multi-task benchmark for long context understanding in LLMs, containing 21 datasets in 6 categories with average lengths of 6711 words (English) and 13386 characters (Chinese).
Gradient and greedy search over token suffixes produces universal, transferable adversarial prompts that elicit objectionable outputs from aligned models including black-box commercial systems.
Analysis of 500k ChatGPT logs shows over one-third of conversations generate fiction, dominated by power users with repetitive and niche patterns.
Low-resource safety failures are action failures because the harmfulness representation transfers but the decision calibration does not; this is fixed by recalibrating a high-resource gate with 1-4 target-language examples.
RWGBench is a citation-centric benchmark for related work generation built from 40k CS papers and a 100-paper test set, with multi-dimensional metrics that better match human expert judgment than standard similarity scores.
Introduces (ε,q,t,A)-behavioral indistinguishability and shows via Qwen/Llama experiments that LoRA distillation boosts semantic similarity but leaves detectable behavioral differences under adversarial evaluation.
A Behavioral Specification interpretive layer improves representational accuracy for AI personalization by compressing user data into patterns, outperforming raw corpora and commercial memory systems on held-out behavioral predictions across 14 autobiographical corpora while reducing context cost.
OR-Space is a benchmark for LLM agents performing full-lifecycle optimization tasks across Build, Revise, and Explain modes in executable multi-artifact workspaces.
Self-evolving rubric with anti-gaming fitness reveals that objective capability scaling fails to transfer to subjective LLM behaviors, with advice-restraint as the universal lowest dimension that can regress.
LogDx-CI benchmark shows hybrid grep+tail reducers achieve top diagnosis quality at low cost, agent loops shrink quality variance across reducers, and cross-family LLM summarizers outperform same-family pairs.
LLMs show severe staleness after training cutoffs and recency bias on historical German statutes; RAG with version filtering mitigates both better than web search.
A multi-agent pipeline iteratively refines topology optimization outputs to match natural language preferences for branched structures, achieving 60% success rate across replicates in cantilever and phone-stand tasks.
Introduces the stochastic-deterministic boundary (SDB) as a load-bearing primitive for LLM agent runtimes and provides a five-step methodology plus catalog of six patterns adapted from distributed systems.
DecisionBench supplies a fixed task suite, model pool, delegation interface, and multi-axis metrics to evaluate emergent delegation, showing similar quality across awareness conditions but 15-31 point headroom under perfect delegation.
SCICONVBENCH is a new benchmark evaluating LLMs on multi-turn disambiguation and inconsistency resolution for task formulation in computational science, with frontier models reaching only 52.7% success on fluid mechanics disambiguation cases.
CBEA with LCV bounds evidence sets and validates commitments before response generation, achieving zero failures in scoped tests at 0.49-0.60 availability versus near-zero for baselines.
Belief Engine is a configurable belief-update mechanism for multi-agent LLM systems that uses structured argument extraction and log-odds stance updates to make evidence-grounded deliberation inspectable and controllable.
Test-Time Hinting trains a hint generator to prepend contextual guidance to VLM prompts, improving accuracy on natural-image VQA benchmarks with generalization to unseen tasks and models.
Presents a likelihood-based benchmark for equation-suffix prediction in technical papers with controls to detect shortcut vulnerabilities in model forecasts.
LLM multi-agent systems on lattices show bias-driven order-disorder crossovers instead of true phase transitions, with extracted effective couplings and fields serving as model-specific fingerprints.
SlimSpec replaces the standard LM-head in draft models with a low-rank version to deliver 4-5x faster speculative decoding while preserving full vocabulary and competitive acceptance rates.
ProactBench measures LLM conversational proactivity in three phases using 198 multi-agent dialogues and finds recovery behavior hard to predict from existing benchmarks.
citing papers explorer
-
DQA: Diagnostic Question Answering for IT Support
DQA maintains persistent diagnostic state and aggregates retrievals at the root-cause level to reach 78.7% success on 150 enterprise IT scenarios versus 41.3% for standard multi-turn RAG while cutting average turns from 8.4 to 3.9.
-
Simulating the Evolution of Alignment and Values in Machine Intelligence
Evolutionary simulations demonstrate that deceptive beliefs fix in AI model populations despite strong test correlations, but combining adaptive tests, better evaluators, and mutations significantly reduces deception.
-
SysTradeBench: An Iterative Build-Test-Patch Benchmark for Strategy-to-Code Trading Systems with Drift-Aware Diagnostics
SysTradeBench evaluates 17 LLMs on 12 trading strategies, finding over 91.7% code validity but rapid convergence in iterative fixes and a continued need for human oversight on critical strategies.
-
Evaluating Artificial Intelligence Through a Christian Understanding of Human Flourishing
Frontier AI models default to procedural secularism and score 17 points lower on Christian human-flourishing criteria than on pluralistic ones, with a 31-point gap in faith and spirituality.
-
Agentic Business Process Management: A Research Manifesto
Agentic Business Process Management reframes BPM around autonomous agents that must exhibit framed autonomy, explainability, conversational actionability, and self-modification to keep their actions aligned with organizational objectives.
-
A Randomized Controlled Trial and Pilot of Scout: an LLM-Based EHR Search and Synthesis Platform
A randomized crossover trial with 20 clinicians showed Scout reduced EHR task completion time by 37.6 percent, lowered workload scores, and met non-inferiority criteria for accuracy, completeness, and relevance versus the EHR alone.
-
ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness
ACE-Bench is an execution-free benchmark that scores LLM coding agents on correct Azure SDK usage via deterministic regex checks and reference-based LLM judges derived from official documentation.
-
Web Retrieval-Aware Chunking (W-RAC) for Efficient and Cost-Effective Retrieval-Augmented Generation Systems
W-RAC decouples extraction from semantic planning via structured units and LLM grouping to match traditional retrieval performance at roughly 10x lower LLM token cost.
-
ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents
ClinicalReTrial is a closed-loop multi-agent system that redesigns textual clinical trial protocols to raise predicted success probability by 5.7% on average while costing $0.12 per trial.
-
Response-Based Knowledge Distillation for Multilingual Jailbreak Prevention Unwittingly Compromises Safety
Distilling safe refusal behavior from OpenAI o1-mini into Llama-3, Gemma-2, and Qwen3 models via response-based LoRA on multilingual jailbreak data increases jailbreak success rates on MultiJail by up to 16.6 points.
-
Reading Between the Lines: The One-Sided Conversation Problem
The one-sided conversation problem is introduced with empirical results showing that future-turn access and utterance length improve missing-turn reconstruction while high-quality summaries are possible without reconstruction on standard dialogue datasets.
-
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
Prompt Duel Optimizer uses dueling bandits and LLM-as-judge pairwise feedback with Double Thompson Sampling and top-performer mutation to find stronger prompts than label-free baselines on BBH and MS MARCO under limited comparison budgets.
-
Don't Pass@k: A Bayesian Framework for Large Language Model Evaluation
A Dirichlet-prior Bayesian estimator for model success probability replaces Pass@k, delivering faster-converging and more stable rankings with credible intervals on math benchmarks.
-
QuiLL: An LLM-Based Vulnerability Assessment Framework for the Wild
QuiLL is a new evaluation pipeline that uses optimized LLM prompts, dynamic in-context learning from an NVD vector store, and a novel accuracy-plus-reasoning metric to benchmark vulnerability detection in real code.
-
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
KG-R1 trains a single RL agent to retrieve from and reason over knowledge graphs in one loop, achieving higher accuracy with fewer tokens than multi-module baselines and transferring to unseen graphs.
-
Fin-PRM: A Domain-Specialized Process Reward Model for Financial Reasoning in Large Language Models
Fin-PRM is a domain-specialized process reward model that supplies binary step-level and trajectory-level supervision signals for financial reasoning in LLMs and outperforms general PRMs on CFLUE and FinQA benchmarks.
-
Listener-Rewarded Thinking in VLMs for Image Preferences
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
-
DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
DeepResearch Bench supplies 100 expert-crafted PhD-level tasks and two human-aligned evaluation frameworks to measure deep research agents on report quality and citation accuracy.
-
Latent Trajectory Dynamics in Large Language Models: A Manifold Evolution Framework with Empirical Validation
DMET models LLM generation as controlled dynamical trajectories on a semantic manifold, with three proxy metrics that predict output quality and support adaptive decoding to lower perplexity.
-
Tuning Language Models for Robust Prediction of Diverse User Behaviors
BehaviorLM applies progressive fine-tuning in two stages to let LLMs predict both frequent anchor and rare tail user behaviors more robustly on real-world datasets.
-
GLM-4-Voice: Towards Intelligent and Human-Like End-to-End Spoken Chatbot
GLM-4-Voice builds an end-to-end spoken chatbot by deriving a 175bps single-codebook tokenizer from ASR, synthesizing interleaved speech-text data, and continuing pre-training of GLM-4-9B on up to 1 trillion tokens before fine-tuning on conversational speech.
-
UNA: A Unified Supervised Framework for Efficient LLM Alignment Across Feedback Types
UNA unifies binary, pairwise, and score-based feedback for LLM alignment via a generalized implicit reward function shown optimal by the log sum inequality.
-
Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models
Empirical analysis shows scaling inference compute via strategies like tree search can be more efficient than scaling model parameters, with 7B models plus novel search outperforming 34B models.
-
Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone
Phi-3-mini (3.8B params, 3.3T tokens) reaches 69% MMLU and 8.38 MT-bench, matching larger models, with scaled-up 7B/14B variants and phi-3.5 extensions for multilingual, MoE, and vision capabilities.
-
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
JailbreakBench supplies an evolving set of jailbreak prompts, a 100-behavior dataset aligned with usage policies, a standardized evaluation framework, and a leaderboard to enable comparable assessments of attacks and defenses on LLMs.
-
Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive
DPOP is a new loss function that prevents DPO from lowering preferred response likelihoods and outperforms standard DPO on diverse datasets, MT-Bench, and enables Smaug-72B to exceed 80% on the Open LLM Leaderboard.
-
EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
EAGLE resolves feature-level uncertainty in speculative sampling via one-step token advancement, delivering 2.7x-3.5x speedup on LLaMA2-Chat 70B and doubled throughput across multiple model families and tasks.
-
Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations
Math-Shepherd is an automatically trained process reward model that scores solution steps to verify and reinforce LLMs, lifting Mistral-7B from 77.9% to 89.1% on GSM8K and 28.6% to 43.5% on MATH.
-
The Falcon Series of Open Language Models
Falcon-180B is a 180B-parameter open decoder-only model trained on 3.5 trillion tokens that approaches PaLM-2-Large performance at lower cost and is released with dataset extracts.
-
Zephyr: Direct Distillation of LM Alignment
Zephyr-7B achieves state-of-the-art chat benchmark results among 7B models by distilling alignment via dDPO on AI feedback preferences, surpassing the 70B Llama-2-Chat model on MT-Bench with no human data required.
-
MemGPT: Towards LLMs as Operating Systems
MemGPT uses OS-inspired virtual context management to extend LLM context windows for large document analysis and long-term multi-session chat.
-
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
LURE reduces object hallucination in LVLMs by 23% via post-hoc revision informed by co-occurrence, uncertainty, and text position analysis.
-
Studying Lobby Influence in the European Parliament
NLP comparison of lobby papers and MEP speeches discovers influence links validated indirectly via retweets and meetings, achieving AUC 0.77 and ideological alignment in aggregate analysis.
-
GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
GPTFuzz is a black-box fuzzing framework that mutates seed jailbreak templates to automatically generate effective attacks, achieving over 90% success rates on models including ChatGPT and Llama-2.
-
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
MAmmoTH models trained via hybrid CoT-PoT instruction tuning on MathInstruct outperform prior open-source LLMs by 16-32% average accuracy on nine math datasets, reaching 33% and 44% on MATH for 7B and 34B scales.
-
Textbooks Are All You Need II: phi-1.5 technical report
phi-1.5 is a 1.3B parameter model trained on synthetic textbook data that matches the reasoning performance of models five times larger on natural language, math, and basic coding tasks.
-
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Multi-agent debate among LLMs yields more reliable text evaluations than single-agent prompting by simulating collaborative human judgment.
-
Large Language Models are not Fair Evaluators
LLMs show strong position bias when scoring model outputs, allowing easy manipulation of rankings, but calibration with multiple evidence, position balancing, and selective human input reduces this bias to better match human judgments.
-
A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language Models
Pilot evaluation of language-specific versus multilingual LoRA adapters on Qwen2.5-VL-3B for curator-guided BLV art descriptions in three languages.
-
A Fixed-Budget, Cluster-Aware Standard for LLM-as-a-Judge Evaluation: A Multi-Hop RAG Stress Test
Proposes a minimum measurement standard for LLM-as-a-judge in multi-hop RAG that fixes budgets and requires cluster-aware inference, showing it alters which baseline comparisons remain significant.
-
LVDrive: Latent Visual Representation Enhanced Vision-Language-Action Autonomous Driving Model
LVDrive improves closed-loop driving on Bench2Drive by adding latent future scene prediction to VLA models via unified embedding space processing and two-stage trajectory decoding.
-
Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks
Pramana defines a typed ClaimAttestation protocol with four variants and verify operations, specifies its lifecycle in TLA+, model-checks it with TLC, and provides a tested Python implementation for auditable agent claims.
-
A Nash Equilibrium Framework For Training-Free Multimodal Step Verification
A Nash equilibrium framework for training-free multimodal step verification that uses cross-modal agreement and disagreement signals for filtering and ranking reasoning steps.
-
Sequential Consensus for Multi-Agent LLM Debates: A Wald-SPRT compute governor with calibration-based failure detection
Adapts SPRT as a compute governor for multi-agent LLM debates using Beta-modeled consensus scores from an LLM judge, yielding 3.7x call reduction on GSM8K at -2pp accuracy versus fixed rounds.
-
QQJ: Quantifying Qualitative Judgment for Scalable and Human-Aligned Evaluation of Generative AI
QQJ is an evaluation framework that anchors LLM judges in expert rubrics and calibrates them on small high-quality annotation sets to improve alignment with human judgment on generative tasks.
-
ChemVA: Advancing Large Language Models on Chemical Reaction Diagrams Understanding
ChemVA framework uses hybrid-granularity visual anchors and entity-name alignment to improve LLM performance on chemical reaction diagrams by ~20 points, reaching 92% structural accuracy on the new OCRD-Bench dataset.
-
Greedy or not, here I come: Language production under vocabulary constraints in humans and resource-rational models
Humans produce language more like greedy local choices than globally optimal planning when vocabulary is tightly constrained, with skilled speakers showing more revision.
-
Tokenizer Fertility and Zero-Shot Performance of Foundation Models on Ukrainian Legal Text: A Comparative Study
Tokenizer fertility varies 1.6x across models on Ukrainian legal text, Qwen uses 60% more tokens than Llama-family models, zero-shot outperforms few-shot by up to 26 points, and pre-war classifiers lose 27.9 points on invasion-era decisions.
-
Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift
Stage-wise DPO constructs hallucination-focused preference pairs near failure boundaries to improve visual grounding in VLMs.
-
When No Benchmark Exists: Validating Comparative LLM Safety Scoring Without Ground-Truth Labels
A formalization of benchmarkless LLM safety scoring validated via an instrumental-validity chain of contrast separation, target variance dominance, and rerun stability, demonstrated on Norwegian scenarios.