Natural Language Processing

This paper introduces a novel notion of intrinsic similarity between language encoders, based on affine homotopy, and demonstrates its strong correlation with extrinsic similarity (downstream task per…

OccamLLM: LLMs now perform accurate arithmetic in a single step!

By cleverly integrating per-example gradient norm calculations during the backward pass of LayerNorm layers, this research enables efficient and accurate gradient noise scale estimation in Transformer…

NoMAD-Attention achieves up to 2x speedup in 4-bit quantized LLaMA inference on CPUs by replacing computationally expensive multiply-add operations with ultra-low-latency in-register lookups.

NoiseGPT uses multi-modal LLMs to detect & fix noisy image labels by identifying probability curvature differences between clean and noisy examples.

This paper introduces InfoNCA and NCA, novel frameworks for language model alignment using noise contrastive estimation, enabling direct optimization from both explicit rewards and pairwise preference…

LLM watermarking faces inherent trade-offs; this paper reveals simple attacks exploiting common design choices, proposing guidelines and defenses for more secure systems.

Neuro-symbolic framework generates high-quality mathematical datasets, enhancing LLMs’ mathematical reasoning capabilities and surpassing state-of-the-art counterparts.

NEST, a novel semi-parametric language model, significantly boosts LLM generation quality, provides accurate source attribution, and achieves a 1.8x speedup in inference time by cleverly incorporating…

Researchers discover ‘safety basins’ in LLMs, proposing a new metric (VISAGE) to quantify finetuning risks and visualize how these basins protect against safety compromise during model training.

SPARTEX achieves memory-efficient extreme multi-label classification by integrating dynamic sparse training with an auxiliary loss function, enabling end-to-end training with millions of labels on com…

MUVERA: Revolutionizing multi-vector retrieval with single-vector speed and accuracy!

MutaPLM: a novel protein language model, provides human-understandable mutation explanations and designs novel mutations with desirable properties using a unique protein delta network and chain-of-tho…

This paper introduces an efficient multivariate stochastic dominance test using optimal transport, enabling robust model benchmarking by considering metric dependencies.

Multi-turn RLHF surpasses single-turn methods by aligning LLMs with human preferences across entire conversations, not just individual turns. A novel mirror-descent algorithm, MTPO, is introduced, pr…

D-LISA: Dynamic modules & language-informed spatial attention revolutionizes multi-object 3D grounding, surpassing state-of-the-art accuracy by 12.8%.

Boosting LLM collaboration, this research introduces a novel theoretical framework for multi-LLM debate, revealing key principles like the effect of similar models and interventions to enhance accurac…

Researchers created MMA, a large multilingual dataset of informal-formal mathematical pairs, leveraging a language model for reverse translation. Fine-tuned models achieved significantly improved aut…

Multi-Head Mixture-of-Experts (MH-MoE) drastically boosts large language model efficiency by activating almost all expert networks, achieving superior performance compared to existing Sparse Mixture-o…

MR-Ben: A new benchmark reveals LLMs’ meta-reasoning flaws, pushing the boundaries of AI evaluation beyond simple accuracy.