Match Task to Objective (MTO) framework for aligning fine-tuning and prompt-tuning strategies with encoder-decoder pre-training objectives
A new arXiv preprint introduces the Match Task to Objective (MTO) framework, which systematically aligns fine-tuning and prompt-tuning strategies with the pre-training objectives of encoder-decoder language models. The work focuses on commonsense knowledge retrieval and generation tasks, reporting over 120% performance gains versus conventional methods in few-shot settings. The framework includes automated methods for preparing task-related data via unsupervised adaptation and novel template design for soft prompt engineering.
Related guides (2)
Related events (8)
MATCHA: Contrastive Semantic Alignment Metric for LLM Evaluation
MATCHA is a new automatic evaluation metric for LLMs that addresses a fundamental flaw in existing metrics: both token-overlap (ROUGE) and embedding-based (BERTScore) metrics routinely assign near-identical scores to semantically contradictory texts. The metric uses a dual-view approach that rewards proximity to a gold reference while penalizing adversarially generated counterfactual contradictions. Evaluated across eight benchmarks spanning QA, summarization, NLI, and semantic similarity tasks, MATCHA outperforms 23 embedding models and achieves 18.38% and 20.82% improvements over ROUGE-L and BERTScore respectively on TruthfulQA. Code and metric are publicly released.
CRAM: Centroid-Routing and Adaptive MoE for Multimodal Continual Instruction Tuning
CRAM is a new method for Multimodal Continual Instruction Tuning (MCIT) that addresses the tension between catastrophic forgetting and parameter efficiency in MLLMs. It combines adaptive-rank instantiation to dynamically allocate parameters based on capability gaps, centroid-guided routing to reuse existing expert knowledge, and an orthogonality penalty to confine new updates to task-specific directions. The approach uses a Mixture-of-Experts architecture where task-specific patterns are isolated into independent modules, avoiding both the interference of shared updates and the parameter bloat of fully isolated expansion. Experiments across diverse benchmarks show consistent improvements over existing MCIT methods.
ProtoAda: Prototype-Guided Adaptive Adapter Expansion for Multimodal Continual Instruction Tuning
ProtoAda is a new framework for Multimodal Continual Instruction Tuning (MCIT) that addresses a key failure mode in sparse Mixture-of-LoRA-Experts architectures: image-text similarity routing is format-blind and incorrectly merges tasks with similar semantics but different output structures (e.g., coordinate prediction vs. VQA). The method introduces format-aware task prototypes to guide both routing and adapter expansion, then consolidates compatible updates geometrically to reuse and refine existing parameters. Experiments across multiple benchmarks show improved performance, particularly on tasks whose answer formats are vulnerable to corruption by sequential fine-tuning.
Q-target framework unifies supervised fine-tuning variants through target distribution design
A new arXiv preprint reframes supervised fine-tuning (SFT) as a problem of target distribution design rather than loss objective selection, introducing the Q-target framework that decomposes SFT supervision into two explicit choices: reliance on the observed token and allocation of remaining probability mass. The authors show that many existing SFT variants can be understood as implicit choices of this target distribution. They propose Target-SFT, which constructs training objectives directly from the desired target distribution, and report consistent improvements across ten reasoning dataset-model settings. The work offers a unifying theoretical lens and opens a broader design space for SFT objectives.
MAS-PromptBench: Systematic study of prompt optimization in multi-agent LLM systems
A new arXiv preprint introduces MAS-PromptBench, a benchmark and study examining when and how much system-prompt optimization improves multi-agent LLM systems (MAS). The authors evaluate two prompt optimizers across diverse MAS configurations varying in task, workflow, communication protocol, and team size. Results show prompt optimization can unlock significant gains but also expose open challenges, particularly around the exponentially growing search space as agent count increases.
Complete-muE: Optimal Hyperparameter Transfer and Scaling for MoE Models
Complete-muE is a framework for transferring hyperparameters across dense FFN and Mixture-of-Experts (MoE) transformer architectures, addressing limitations of existing tools like μP and SDE that cannot handle simultaneous architecture and token-per-expert changes. It uses a two-bridge system: Bridge I maps dense FFN to Dense MoE via active-width μP with normalized router scale, and Bridge II maps Dense MoE to sparse MoE via activated-expert scaling with a first-order SDE correction. The practical outcome is a 'tune dense once, transfer to all' recipe that enables near-optimal hyperparameter reuse across MoE configurations without costly re-tuning. Experiments on language model and diffusion model pretraining confirm stable hyperparameter optima across architectures and parameter counts.
Failure Modes of Multi-Objective Prompt Optimization for LLM Judges
This paper investigates multi-objective prompt optimization for LLM-as-judge systems, testing five decomposition modes of textual gradient optimizers across varying levels of cross-task information sharing. In 6 of 10 configurations, optimization fails to improve over the initial prompt, with gradient specificity dropping 59% when multiple criteria are processed jointly. The authors identify two separable failure modes: gradient dilution at optimization time and instruction interference at inference time. These findings constrain the design space for customizing LLM judges via textual feedback across multiple evaluation criteria simultaneously.
TuneJury: Open pairwise reward model for text-to-music preference alignment
Researchers introduce TuneJury, an open-source instance-level pairwise reward model for text-to-music generation that predicts preference scores from text prompts and audio clips. The model is trained on publicly available human-preference labels spanning arena votes, crowdsourced comparisons, and expert ratings. A post-hoc anchor calibration method enables efficient adaptation to new generators without full retraining. The reward model drives gains across best-of-N selection, latent optimization, and expert-iteration post-training.