natural language processing

How do World Models and Policies Compose in LLM Agents? A Joint Spectral and Behavioral Account

The findings suggest world knowledge and task-directed ability can be learned in geometrically complementary forms, and that future post-training pipelines should consider how best to engineer the interface between them.

On the Recoverability of Private Information Unlearning in Large Language Models

Large language models (LLMs) can memorize sensitive information, raising serious privacy concerns. Machine unlearning offers a potential solution to remove such information, but it remains unclear whether existing methods truly erase it or merely hide it within the model. A key challenge is quantifying the persistence of sensitive data under a unified evaluation framework. To address this, we construct a synthetic dataset containing fake private information and propose a white-box auditing framework to systematically assess whether claimed-forgotten information is genuinely removed. Using this framework, we evaluate five existing unlearning methods and find that a simple"inverse greedy"decoding -- selecting the least likely token at each step -- can recover supposedly forgotten private information. Our results reveal that current unlearning approaches often fail to fully eliminate sensitive information, highlighting the need for more reliable methods to ensure privacy in deployed LLMs.

Higher-Dimensional Rotary Position Embedding

HDR-RoPE is proposed, which extends RoPE from independent 2D rotations to higher-dimensional rotations and introduces a Paley-I orthogonal basis to obtain balanced, isotropic, and dense phase mixing within each rotation subspace and significantly enhances channel coupling and rotational degrees of freedom while maintaining orthogonal stability and the relative position closure property.

Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space

While surface prompting fails to recover diversity, entrance-targeted interventions succeed: late-layer parameter interpolation with early checkpoints increases solution coverage by 37% at no loss in pass@1 and late-layer parameter interpolation with early checkpoints increases solution coverage by 37% at no loss in pass@1.

SemKV: Semantic Mixed-Precision KV Cache Quantization Guided by the Quality Cliff for Long-Context LLM Inference

The key-value (KV) cache is the dominant memory bottleneck of long-context large language model (LLM) inference, growing linearly with context length. We show that uniform KV quantization on a fractional-bit grid does not degrade gracefully: under a prespecified multi-seed statistical protocol, Llama-3.1-8B-Instruct with an affine quantizer is statistically indistinguishable from FP16 KV down to 2.322 code bits/value and collapses at 2.0 bits - a quality cliff in (2.0, 2.322] that reappears in generation-time quantization and multi-turn dialogue and transfers to Mistral-7B. The cliff reframes importance-aware mixed precision: above it, eight model-internal importance indicators are statistically interchangeable, so the benefit of mixing is grid interpolation, reaching average precisions uniform quantization cannot realize. SemKV preserves every token, ranks tokens by a model-internal score, and assigns two adjacent above-cliff precisions, achieving a measured 6.0x storage reduction with no statistically detectable quality difference from full KV (n=900, three seeds), and outperforming FP16 token pruning granted a 1.5x larger memory budget. Replacing the affine base with a distortion-optimized quantizer (TurboQuant-MSE) lowers the cliff in every protocol tested, raising the no-detectable-loss operating point to 7.9x. The recipe: measure the cliff for the target deployment setting, then interpolate above it.

The Halt Vector: Internalizing a Causal Steering Intervention for Efficient Reasoning

The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing, and what works is reconstructing the whole steered activation with those dimensions pinned to their natural values.

SPEAR: Distilling Domain-Adaptive Reasoning Skeletons via Sequential Symbolic Alignment in Reinforcement Learning

This work introduces SPEAR (Symbolic Process Evaluation and Alignment Reward), a training-free and plug-and-play process reward method for sequence-level on-policy distillation that effectively bridges the reasoning gap between student and teacher models via sequence-level distillation with efficient dense process rewards.

Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs

Slot2Text, a dual-mode surgical MLLM that replaces dense representations of visual input with a compact set of regions encoded as slot latents, establishes compact slot latents as an efficient default visual interface for surgical MLLMs, with grounded reasoning invoked when greater spatial traceability is required.

Application of agile processes in complex systems development projects

The ITEA AGILE project shows that the application of agile software development methods and processes can offer an up to 70% reduction in lead time and costs in a wide range of different industry sectors.

Is management commitment a necessity after all in software process improvement?

Literature and practice has established that the lack of management commitment has been one of the top reasons for a failed SPI (software process improvement) initiative. The paper reports results from an ongoing study aimed at clarifying the role and the meaning of management commitment in SPI initiatives. Results from five focused interviews with SPI professionals are reported together with results from 12 SPI initiatives where the level of management commitment (in terms of concrete signs) was measured in order to test whether it would correlate with the level of success of an SPI initiative. In contrast with the evidence from the literature, the results show that none of the signs of management commitment correlated significantly with the success of the SPI initiatives. It is suggested that the concept of champion may have explained the SPI project success better than management commitment. The paper concludes that many of the SPI initiatives do not require management commitment beyond obtaining the resources needed.

Rethinking the Concept of Commitment in Software Process Improvement

It is shown that current thinking relies on models of commitment that are flawed in both academic and practical sense and four misconceptions are identified in current thinking.

Commitment development in software process improvement: critical misconceptions