Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

3577141,0711,428 · Jun 202019922001200920172026
48 results for model alignment

Conformal Alignment ensures trustworthy outputs from foundation models.

problem Ensuring outputs from foundation models align with human values in high-stakes tasks.
method A framework that trains an alignment predictor using reference data to select trustworthy outputs.
result Conformal Alignment accurately identifies trustworthy outputs via lightweight training over moderate reference data.

Inference-aware meta-alignment of LLMs reduces computational cost.

problem Aligning LLMs to diverse human preferences is challenging due to conflicting criteria.
method IAMA trains a base model to be aligned to multiple tasks via different inference-time alignment algorithms, using non-linear GRPO for optimization.
result IAMA enables effective alignment of LLMs to multiple criteria with limited computational budget.

Unified framework for aligning and composing diffusion models to satisfy multiple constraints.

problem Improving quality and compliance of generated samples from diffusion models.
method Constrained optimization framework that unifies alignment and composition of diffusion models.
result Proposed framework effectively satisfies multiple constraints in image generation.

Sparse text alignments learned via optimal transport improve model explainability.

problem Building self-explaining models by selecting relevant text pieces.
method Employing optimal transport to find minimal cost alignments, introducing constrained variants for sparsity.
result Sparse and interpretable alignments achieved, preserving prediction accuracy.

SAIL improves online alignment of large language models with minimal feedback.

problem Offline RLHF methods often lead to sub-optimal performance due to fixed preference datasets.
method SAIL uses bilevel optimization and a single-level first-order method to iteratively refine model alignment.
result SAIL significantly improves alignment performance on open-sourced datasets with minimal computational overhead.

The paper examines how spike strengths and alignments affect overfitting in linear regression models.

problem The impact of spike strengths and alignments on overfitting in linear regression models.
method Characterization of generalization error through exact expressions and analysis of spike strengths, aspect ratio, and target alignment.
result Increasing spike strength can lead to catastrophic overfitting before benign overfitting, especially in well-specified aligned problems.

Direct Density Ratio Optimization aligns LLMs with human preferences without assuming specific models.

problem Statistical inconsistency in aligning LLMs with human preferences.
method Direct Density Ratio Optimization (DDRO) estimates density ratio directly.
result DDRO is statistically consistent, converging to true human preferences as data grows.

LPL optimizes embeddings to align local neighborhoods, improving cross-lingual word alignment.

problem Aligning embeddings across different datasets and languages.
method Locality Preserving Loss (LPL) optimizes model to project embeddings while maintaining local neighborhoods and aligning them.
result LPL-based alignment leads to better and consistent accuracy, especially in small training set settings.

A new protocol corrects confounding effects to measure alignment-induced activation shifts accurately.

problem Confounding effects in measuring alignment-induced activation shifts using naive methods.
method Introduces a four-variant decomposition to separate alignment shift from template effects.
result Correctly measures alignment-induced activation shifts, recovering behaviorally active subspace.

The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.

problem Aligning LLMs with human preferences using game theory.
method Systematic study of payoff choices in a two-player zero-sum game for desirable alignment properties.
result Impossibility of preference matching in game-theoretic LLM alignment under standard assumptions.

The paper proposes a method to align AI models using conformal risk control.

problem Aligning AI models to meet end-user requirements in non-generative settings.
method Post-processing a pre-trained model to better align with a subset of functions using conformal risk control.
result A probabilistic guarantee that the resulting conformal interval around a model contains a function approximately satisfying a desired property.

Extends reinforcement learning alignment to scalar rewards, improving math reasoning.

problem Designing reinforcement learning algorithms for general LLM alignment.
method Introduces f-GRPO and f-HAL, estimating f-divergences between reward-aligned and unaligned distributions.
result Improves math reasoning RLVR tasks and mitigates reward hacking.

Sequence-to-sequence text-to-speech (TTS) is dominated by soft-attention-based methods. Recently, hard-attention-based methods have been proposed to prevent fatal alignment errors, but their sampling method of discrete alignment is poorly investigated. This research investigates various combinations of sampling methods…

2019-10-28abs ↗pdf ↗

New model optimizes feature alignment, improving statistical and computational efficiency.

problem Statistical and computational challenges in feature alignment.
method Covariance alignment model, Gromov-Wasserstein algorithm.
result Gromov-Wasserstein algorithm is minimax optimal and practical for covariance alignment.

Improved text-to-image alignment using iterative VQA feedback.

problem Misalignment between text prompts and generated images, especially for complex inputs.
method Decompose complex prompts into assertions, evaluate each using VQA, combine scores iteratively.
result Significantly higher correlation with human ratings compared to CLIP, BLIP scores.

We present a probabilistic model for unsupervised alignment of high-dimensional time-warped sequences based on the Dirichlet Process Mixture Model (DPMM). We follow the approach introduced in (Kazlauskaite, 2018) of simultaneously representing each data sequence as a composition of a true underlying function and a time…

2018-11-26abs ↗pdf ↗

Paper addresses online alignment of large language models under uncertain preference feedback.

problem Online alignment of large language models with misspecified preference feedback.
method Formulates an oracle-robust objective as a worst-case optimization problem for log-linear policies, and develops projected stochastic composite updates.
result Shows that the robust objective admits an exact closed-form decomposition and achieves O~(ε2)\widetilde{O}(\varepsilon^{-2}) oracle complexity.

Novel alignment framework for text-to-image generation using diffusion models and flow matching.

problem Improving text-to-image generation with minimal computational resources.
method Proposes a novel alignment framework that decomposes the score function into pre-trained score plus a conditional expectation of the reward.
result Achieves comparable performance to finetuning-based models with reduced computational cost.

The paper addresses poor calibration in fine-tuned LLMs after preference alignment.

problem Poor calibration in fine-tuned Large Language Models (LLMs) after preference alignment.
method Proposes a calibration-aware fine-tuning approach to restore calibration without compromising model performance.
result Demonstrates the effectiveness of the proposed methods through extensive experiments.

Align-RUDDER improves reinforcement learning with few demonstrations by redistributing rewards.

problem Learning complex tasks with sparse and delayed rewards using few demonstrations.
method Align-RUDDER uses a profile model for reward redistribution based on multiple sequence alignment of demonstrations.
result Align-RUDDER outperforms competitors on complex tasks with few demonstrations.

The study explains how neural networks align their kernels to target functions during training.

problem Understanding how neural networks align their kernels to target functions during training.
method Theoretical analysis of kernel evolution in toy models and deep networks.
result Kernel alignment naturally emerges during training to accelerate convergence and improve generalization.

A new method reduces the computational burden of safety alignment for large language models.

problem Safety concerns in large language models and the need to align them with human preferences.
method Optimal dualization approach to reduce constrained alignment to an unconstrained problem.
result Our algorithms MoCAN and PeCAN significantly reduce computational burden and improve training stability.

This paper improves model fusion by training-time neuron alignment, reducing barriers in multi-model fusion.

problem Diverse neuron permutations across different settings hinder model fusion performances.
method Training-time neuron alignment using fixed neuron anchors to reduce training-time permutations.
result Training-time neuron alignment improves fusion of pretrained models and federated learning performances.

The infinite Viterbi alignment is the limiting maximum a-posteriori estimate of the unobserved path in a hidden Markov model as the length of the time horizon grows. For models on state-space Rd\mathbb{R}^{d} satisfying a new ``decay-convexity'' condition, we develop an approach to existence of the infinite Viterbi ali…

2018-10-08abs ↗pdf ↗

PILAF optimizes reward models from human feedback for better policy alignment.

problem Creating accurate reward models from human feedback for policy optimization.
method Policy-Interpolated Learning for Aligned Feedback (PILAF) that explicitly aligns preference learning with maximizing underlying oracle reward.
result PILAF is optimal from both optimization and statistical perspectives, demonstrating strong performance in RLHF settings.

SONA improves conditional generation by balancing authenticity and alignment.

problem Challenges in balancing authenticity and conditional alignment in conditional generative models.
method SONA integrates unconditional discrimination, matching-aware supervision, and adaptive weighting to balance authenticity and alignment.
result SONA achieves superior sample quality and conditional alignment compared to state-of-the-art methods.

Aligns attention distributions for improved accuracy and robustness.

problem Improving the accuracy and robustness of neural networks using attention mechanisms.
method Alignment attention that encourages key and query distributions to match within each head.
result Alignment attention leads to better accuracy, uncertainty estimation, and robustness across various tasks.