Category
2,394 papers
An automatic multi-token debiasing pipeline called General Phrase Debiaser, which is capable of mitigating phrase-level biases in masked language models, and can significantly reduce gender biases on both career and multiple disciplines, across models with varying parameter sizes.
BLOOM-WILT is introduced, a full auditing pipeline that elicits natural multi-turn instances of rare behaviours, without training cost or access beyond the target's next-token distribution and raises average behaviour presence from 51% to 100% when eliciting self-harm encouragement from Qwen3.5-4B.
This work proposes agentic data cracking, a method that structures unstructured data adaptively and speculatively as a byproduct of reasoning itself, a first step toward next-generation data infrastructure for agentic reasoning over unstructured data.
In an application to 363 U.S. metropolitan areas, embedding-based clusters of LLM-generated economic descriptions recover interpretable economic archetypes and separate local employment dynamics more sharply than clustering on model residuals, or on a curated set of industry and demographic covariates.
Reach audiences
Advertise in front of researchers, engineers, and readers.
A clinician-support framework in which post-session interviewer ratings are combined with automatic language-based predictions to estimate patient-reported interaction quality in free clinical interviews is evaluated, suggesting that automatic language analysis and interviewer judgment capture complementary aspects of patient experience.
A Hermon moment is called: the point at which an AI society acquires, for human understanding, a beginning, the point at which an AI society acquires, for human understanding, a beginning.
A conceptual framework and roadmap for addressing four interrelated translational failure domains through rigorous validation, uncertainty-aware methods, interoperable infrastructures, regulatory alignment, and human oversight across the AI lifecycle is proposed.
HSRM is introduced, a lightweight hidden-state reward model that verifies candidate solutions by directly reading the generator's internal representations rather than re-processing its text, providing an efficient alternative to text-only verification by reusing representations already computed during generation.
The vocal music of each language carries a distinctive sonic identity, even without instrumental accompaniment. We ask whether these differences are measurable and traceable to specific phonemes. To tackle this question, we introduce phoneme-conditional analysis, which isolates the acoustic effect of typologically distinctive phonemes by comparing marker syllables against matched non-marker controls within the same song, holding singer, melody, and genre constant. Across nine typologically diverse languages and thousands of songs, we measure effects along five acoustic dimensions. Song-level profiles built from these effects identify the language of an unaccompanied vocal at 85.5% balanced accuracy in a nine-way classification with folds grouped by artist; whether the separability arises by accumulation of the phoneme-local effects themselves is left open. Our findings suggest that phonological structure leaves systematic and measurable traces in how each language is sung.
This work finds that jailbreak robustness is highly fragile to operational-state variation: even when the attack remains fixed, changing only an ordinary system prompt not designed to affect safety can dramatically alter attack success rates.
CIPR (Coding In Poisoned Repos), the first benchmark that systematically varies PLCs in poisoned real-world repositories, is introduced and highlights that coding agent vulnerability is not a static property, but a dynamic outcome shaped by everyday user configurations.
This work formulate multi-turn reasoning as a hidden-state trajectory of the underlying LLM that is characterized via two complementary signals: temporal curvature that captures the directional consistency of turn-to-turn updates, and variance slope which measures the expansion or contraction of the exploration space.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
With millions of users across the world, Julia has been used to conduct cutting-edge research and to design new drugs, jet engines, heat pumps, and more.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.
Algorithms & Theory
New MIT research could lead to better materials for a fossil-fuel-free process for making the chemical that's essential to fertilizer and other products.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
