While counterfactual fairness of point predictors is well studied, its extension to prediction sets--central to fair decision-making under uncertainty--remains underexplored. On the other hand, conformal prediction (CP) provides efficient, distribution-free, finite-sample valid prediction sets, yet does not ensure counterfactual fairness. We close this gap by developing Counterfactually Fair Conformal Prediction (CF-CP) that produces counterfactually fair prediction sets. Through symmetrization of conformity scores across protected-attribute interventions, we prove that CF-CP results in counterfactually fair prediction sets while maintaining the marginal coverage property. Furthermore, we empirically demonstrate that on both synthetic and real datasets, across regression and classification tasks, CF-CP achieves the desired counterfactual fairness and meets the target coverage rate with minimal increase in prediction set size. CF-CP offers a simple, training-free route to counterfactually fair uncertainty quantification.

Code Large Language Models (LLMs) are revolutionizing software engineering. However, scaling laws that guide the efficient training are predominantly analyzed on Natural Language (NL). Given the fundamental differences like strict syntax between code and NL, it is unclear whether these laws are directly applicable to code. To address this gap, we conduct the first large-scale empirical study of scaling laws for code, comprising 117 experimental runs with model sizes from 0.2B to 3.8B and training tokens from 2B to 128B. We fit the Chinchilla law and the Farsser law. First, the results show that the more expressive Farseer law offers greater accuracy. Second, the analysis reveals that Code LLMs scale effectively with model size. Crucially, code represents a more data-hungry regime, requiring a substantially higher data-to-parameter ratio than NL. Finally, two additional sets of experiments on code-NL mixtures show that NL benefits resource-constrained scenarios, but becomes a detriment at higher compute budgets.

Inspired by the principle of self-regulating cooperation in collective institutions, we propose the Group Relative Policy Optimization with Global Cooperation Constraint (GRPO-GCC) framework. This work is the first to introduce GRPO into spatial public goods games, establishing a new deep reinforcement learning baseline for structured populations. GRPO-GCC integrates group relative policy optimization with a global cooperation constraint that strengthens incentives at intermediate cooperation levels while weakening them at extremes. This mechanism aligns local decision making with sustainable collective outcomes and prevents collapse into either universal defection or unconditional cooperation. The framework advances beyond existing approaches by combining group-normalized advantage estimation, a reference-anchored KL penalty, and a global incentive term that dynamically adjusts cooperative payoffs. As a result, it achieves accelerated cooperation onset, stabilized policy adaptation, and long-term sustainability. GRPO-GCC demonstrates how a simple yet global signal can reshape incentives toward resilient cooperation, and provides a new paradigm for multi-agent reinforcement learning in socio-technical systems.

Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models (LLMs) during inference. Notably, popular inference engines, such as vLLM, enable users to conveniently prune downloaded models before they are deployed. While the utility and efficiency of pruning methods have improved significantly, the security implications of pruning remain underexplored. In this work, for the first time, we show that modern LLM pruning methods can be maliciously exploited. In particular, an adversary can construct a model that appears benign yet, once pruned, exhibits malicious behaviors. Our method is based on the idea that the adversary can compute a proxy metric that estimates how likely each parameter is to be pruned. With this information, the adversary can first inject a malicious behavior into those parameters that are unlikely to be pruned. Then, they can repair the model by using parameters that are likely to be pruned, effectively canceling out the injected behavior in the unpruned model. We demonstrate the severity of our attack through extensive evaluation on five models; after any of the pruning in vLLM are applied (Magnitude, Wanda, and SparseGPT), it consistently exhibits strong malicious behaviors in a diverse set of attack scenarios (success rates of up to $95.7\%$ for jailbreak, $98.7\%$ for benign instruction refusal, and $99.5\%$ for targeted content injection). Our results reveal a critical deployment-time security gap and underscore the urgent need for stronger security awareness in model compression.

As large language models (LLMs) are deployed globally, creating pluralistic systems that can accommodate the diverse preferences and values of users worldwide becomes essential. We introduce EVALUESTEER, a benchmark to measure LLMs' and reward models' (RMs) steerability towards users' value and stylistic preference profiles grounded in psychology and human-LLM interaction literature. To address the gap in existing datasets that do not support controlled evaluations of RM steering, we synthetically generated 165,888 preference pairs -- systematically varying pairs along 4 value dimensions (traditional, secular-rational, survival, and self-expression) and 4 style dimensions (verbosity, readability, confidence, and warmth). We use EVALUESTEER to evaluate whether, given a user profile and a pair of candidate value-laden and style-laden responses, LLMs and RMs are able to select the output that aligns with the user's preferences. We evaluate six open-source and proprietary LLMs and RMs under eleven systematic prompting conditions and six preference comparison scenarios. Notably, our results show that, when given the user's full profile of values and stylistic preferences, the best models achieve <75% accuracy at choosing the correct response, in contrast to >99% accuracy when only relevant style and value preferences are provided. EVALUESTEER thus highlights the limitations of current RMs at identifying and adapting to relevant user profile information, and provides a challenging testbed for developing RMs that can be steered towards diverse human values and preferences.

Abstract--As Large Language Models (LLMs) gain wider adoption, ensuring their reliable handling of Personally Identifiable Information (PII) across diverse regulatory contexts has become essential. This work introduces a scalable multilingual data curation framework designed for high-quality PII annotation across 13 underrepresented locales (Table I), covering approximately 336 locale-specific PII types. Our phased, human-in-the-loop annotation methodology combines linguistic expertise with rigorous quality assurance, leading to substantial improvements in recall and false positive rates from pilot, training, and production phases. Beyond reporting empirical gains, we highlight common annotator challenges in multilingual PII labeling and demonstrate how iterative, analytics-driven pipelines can enhance both annotation quality and downstream model reliability. I. Introduction A. PII Data Protection The surge in user-generated content has led to vast textual corpora containing hidden instances of Personally Identifiable Information (PII) in application forms, support tickets, reviews and social media posts [1]. PII--such as NAME, SSN, and PHONE NUMBER--poses significant privacy risks if not handled correctly. Its compromise can result in identity theft, financial fraud, and unauthorized access to sensitive data [2].

'Four dead and 12 injured' in Mississippi shooting after people descend on town for homecoming game Joe Biden, 82, receiving new treatment after'aggressive' cancer spread to his bones REVEALED: The secret George Soros network'behind America's street chaos'... and the dossier that shows how to stop it Tinnitus destroyed Peter's life but doctors dismissed him. Then he tried an extraordinary drug-free University of Cambridge-backed treatment that gives instant relief - no wonder medics say it's so'exciting' KENNEDY: Obama's bitter post about Trump's Gaza peace deal proves what I've long suspected about Barry... and it would make Sigmund Freud blush Gold is soaring... here's what the pros say you should do with your 401(k) before it's too late Model dubbed'the world's most beautiful girl' when she was six is now all grown up and looks VERY different as she poses up a storm at Paris Fashion Week Teacher was'so high on cocaine she thought one of her students was her dog' But now, a royal insider claims they're'just as entitled as their parents' with'shady friends' Heartbreaking moment NFL reporter makes brutal comment about player Xavier Legette's dead father in locker room interview Experts reveal the surprising TRUTH behind RFK Jr's link between circumcision and autism Bombshell records that damn Letitia James and show Trump was RIGHT... and the staggering sum she was swindling Trump starts DOGE 2.0 as mass layoffs take place across federal government amid shutdown Famed'Big Short' investor gives terrifying verdict on Trump hammering China with 100 PERCENT tariff... and issues doomsday warning to Wall Street Jennifer Aniston, you've betrayed every woman with your selfish admission about not having children: CAROLINE BULLOCK Nasa has unveiled plans to send astronauts to live on the moon - inside glass bubbles made from lunar dust. The American space agency is funding research into the large livable spheres which would be created in situ, the Telegraph reports. Tiny pieces of so-called lunar glass - a component of the moon's soil, or regolith, along with rocks and mineral fragments - would be collected upon arrival from Earth. The material would be melted down using the same technology as in a domestic microwave oven, along with a'smart microwave furnace'.

'Four dead and 12 injured' in Mississippi shooting after people descend on town for homecoming game Joe Biden, 82, receiving new treatment after'aggressive' cancer spread to his bones REVEALED: The secret George Soros network'behind America's street chaos'... and the dossier that shows how to stop it Tinnitus destroyed Peter's life but doctors dismissed him. Then he tried an extraordinary drug-free University of Cambridge-backed treatment that gives instant relief - no wonder medics say it's so'exciting' KENNEDY: Obama's bitter post about Trump's Gaza peace deal proves what I've long suspected about Barry... and it would make Sigmund Freud blush Gold is soaring... here's what the pros say you should do with your 401(k) before it's too late Model dubbed'the world's most beautiful girl' when she was six is now all grown up and looks VERY different as she poses up a storm at Paris Fashion Week Teacher was'so high on cocaine she thought one of her students was her dog' But now, a royal insider claims they're'just as entitled as their parents' with'shady friends' Heartbreaking moment NFL reporter makes brutal comment about player Xavier Legette's dead father in locker room interview Experts reveal the surprising TRUTH behind RFK Jr's link between circumcision and autism Bombshell records that damn Letitia James and show Trump was RIGHT... and the staggering sum she was swindling Trump starts DOGE 2.0 as mass layoffs take place across federal government amid shutdown Famed'Big Short' investor gives terrifying verdict on Trump hammering China with 100 PERCENT tariff... and issues doomsday warning to Wall Street Jennifer Aniston, you've betrayed every woman with your selfish admission about not having children: CAROLINE BULLOCK Meteorologist's stark warning to Americans to brace for a harsh winter with less snow but more nor'easters Meteorologists are already predicting what the winter months will bring, with some regions of the US expected to see less snow than last year, and nor'easters anticipated to ravage parts of the Northeast. Paul Pastelok, chief meteorologist for AccuWeather's long-range forecasting team, told the Daily Mail that while he didn't expect above normal snowfall for the winter season, he warned that those in the Northeast should brace for nor'easters and it would still be a harsh winter. Pastelok explained that the nor'easter over this weekend is on trend with what is to come, as rapidly developing storms come in off the East Coast. 'People may say, Well, you're forecasting less snow, so it doesn't look like a harsh winter.

'Four dead and 12 injured' in Mississippi shooting after people descend on town for homecoming game Joe Biden, 82, receiving new treatment after'aggressive' cancer spread to his bones REVEALED: The secret George Soros network'behind America's street chaos'... and the dossier that shows how to stop it Tinnitus destroyed Peter's life but doctors dismissed him. Then he tried an extraordinary drug-free University of Cambridge-backed treatment that gives instant relief - no wonder medics say it's so'exciting' KENNEDY: Obama's bitter post about Trump's Gaza peace deal proves what I've long suspected about Barry... and it would make Sigmund Freud blush Gold is soaring... here's what the pros say you should do with your 401(k) before it's too late Model dubbed'the world's most beautiful girl' when she was six is now all grown up and looks VERY different as she poses up a storm at Paris Fashion Week Teacher was'so high on cocaine she thought one of her students was her dog' But now, a royal insider claims they're'just as entitled as their parents' with'shady friends' Heartbreaking moment NFL reporter makes brutal comment about player Xavier Legette's dead father in locker room interview Experts reveal the surprising TRUTH behind RFK Jr's link between circumcision and autism Bombshell records that damn Letitia James and show Trump was RIGHT... and the staggering sum she was swindling Trump starts DOGE 2.0 as mass layoffs take place across federal government amid shutdown Famed'Big Short' investor gives terrifying verdict on Trump hammering China with 100 PERCENT tariff... and issues doomsday warning to Wall Street Jennifer Aniston, you've betrayed every woman with your selfish admission about not having children: CAROLINE BULLOCK I discovered secret tunnels below Egypt's Giza pyramids... and they may lead to a forgotten underworld On the northeastern edge of the Giza Plateau, I discovered three perfectly cut shafts hidden beneath the sands. They sit in the triangle between the Great Sphinx, Khufu's Pyramid and Khafre's Pyramid, and may open into a long-forgotten underground world. These are not water wells. They bear no inscriptions, no signs of casual digging, and their geometry is too precise, their walls too smooth, their design too deliberate.

America needs tax breaks for tradesmen to solve skilled worker shortages threatening national security and infrastructure.