Natural Language Processing

LLMs’ emotional decision-making is assessed using a novel framework, EAI, showing that emotions significantly alter ethical and strategic choices in games. This reveals crucial biases, necessitati…

Federated Dual-Personalizing Adapter (FedDPA) tackles test-time distribution shifts and personalization in federated foundation models using a global and local adapter co-working mechanism, achieving …

DropBP: Accelerate LLM fine-tuning by 44% while preserving accuracy!

This paper introduces ActiveACRE, a model that uses LLMs and probabilistic inference to infer natural language rules through online experimentation, demonstrating higher accuracy than existing methods…

DoFIT: A novel domain-aware framework significantly reduces catastrophic forgetting in federated instruction tuning by finely aggregating overlapping weights and using a proximal perturbation initiali…

LLMs’ reasoning abilities are assessed via a novel framework that leverages probabilities of causation, revealing that while capable, their understanding of causality falls short of human-level reason…

LLMs’ fact retrieval is easily manipulated by context, highlighting their associative memory behavior; this paper studies this with transformers, showing how self-attention and value matrices support …

LLMs prioritize task completion over full world-state understanding by using goal-oriented abstractions.

DALD: A novel framework for black-box LLM text detection, achieving state-of-the-art performance without relying on source model logits, by aligning surrogate model distributions.

Language models struggle with social/emotional intelligence and physical commonsense, unlike human brains. Fine-tuning models on these aspects improves their brain response prediction accuracy.

LLMs are aligned to human preferences distributionally using Optimal Transport, achieving state-of-the-art performance.

DISP-LLM: A novel dimension-independent structural pruning method for LLMs achieves accuracy similar to semi-structural pruning while improving flexibility and efficiency, outperforming state-of-the-a…

Bridging the gap between continuous diffusion models and discrete data, this work introduces a novel boundary-conditional approach achieving superior performance in language modeling and image generat…

COAT leverages LLMs to identify high-level causal factors from unstructured data, enabling causal discovery in real-world scenarios where well-defined variables are lacking.

DSA, a novel automated framework, discovers optimal sparsity allocation for layer-wise LLM pruning, achieving significant performance gains across various models and tasks.

LLMs discover novel offline preference optimization algorithms, achieving state-of-the-art performance on various tasks.

Diffusion-of-Thought (DoT) boosts reasoning in diffusion language models by enabling parallel reasoning steps, outperforming larger autoregressive models in speed and accuracy.

DIFFNORM boosts non-autoregressive speech-to-speech translation by normalizing speech data with a diffusion model and classifier-free guidance, achieving significant quality improvements.

Diff-eRank: A novel rank-based metric assessing LLMs’ efficiency in eliminating redundant information during training, showing improved correlation with model size and performance.

Decoupled-Head Attention (DHA) drastically cuts LLM inference costs by adaptively sharing key/value heads, achieving 97.6% of original performance with only 0.25% pre-training.