overfeed.news
Anuncio

Privum

Construimos, protegemos y operamos tu infraestructura digital.

Software, sistemas de IA, pruebas de penetración y nube segura para empresas.

Hablar con Privum

Tema

LLMs

3009documentos

251últimos 7 días

arXiv AI Papers

Humans Correct Their Judgments Through Debate, but Weaker AI Models Do Not

How can we effectively oversee AI systems that surpass human intelligence? AI Safety via Debate proposes that two AI systems argue opposing positions and a judge, either a human or a weaker model, decides which is correct. By facilitating supervisors in providing high-quality training signals, debate aims to encourage truthful and safe behavior from AI systems whose capabilities exceed our own. However, human judgment is not neutral: people often rely on biases which advanced AI systems may learn to exploit. Drawing on insights from collective intelligence and social cognition, this paper investigates whether debate can guide human and LLM supervisors toward the truth despite their prior beliefs. We evaluate several protocol configurations. We also explore setups inspired by the wisdom of the crowd such as the number and diversity of judges, as well as interaction mechanisms including deliberation and voting. Overall, we find that debate increases accuracy relative to prior beliefs for human judges, whereas the consultancy baseline, in which a single expert argues for one answer, does not. For weaker language models, however, the results are mixed: debate provides no comparable gains in most settings and can even reduce accuracy. Among multi-judge protocols, weighted voting produces the highest accuracy for human supervisors, whereas for LLMs none of them significantly improves group accuracy, even as the number of judges increases. Notably, the behavior of minority judges in non-diverse deliberation protocols suggests that, under symmetric settings, incorrect positions could be more persuasive than correct ones. These findings support debate as a viable path toward scalable human oversight, but cast doubt on its benefits for weaker AI supervisors, raising concerns about fully automated training and control pipelines in high-stakes settings.

en
arXiv AI Papers

DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM Systems

Decision models support routing, guardrails, and output verification in LLM systems. However, item accuracy alone cannot establish whether models make correct decisions across controlled variations or assign reliable confidence to their predictions. We introduce DecisionPivot, a diagnostic benchmark comprising 48 tasks and 40,033 items across seven decision roles. Its core track contains 7,800 items from 13 generated task families, organized into contrast groups with computed answers verified by independently implemented solvers. The complementary reference track contains 32,233 items from 35 public test sets, preserving their original evaluation metrics. We evaluate 40 decision models and 14 general models using documented, model-specific protocols, assessing item and contrast-group accuracy, probability ordering, calibration, and empirical selective coverage. Our results reveal substantial differences obscured by aggregate scores: two 27B models separated by only 2.6 points on the reference track achieve contrast-group accuracies of 70.1% and 44.2%. Across 2,400 binary contrast pairs, Perplexity Decider correctly ranks the positive member above the negative member in 92.3% of pairs but answers both members correctly in only 74.1%, exposing a gap between probability ordering and decision correctness. Models with similar item accuracy also differ in the reliability of their high-confidence predictions. On a separate 1,296-item subset, GLM-5.3 achieves 93.5\% contrast-group accuracy at a higher reasoning setting, compared with 81.5% at its lowest effort. By linking errors to pivotal details and difficulty levels, DecisionPivot provides fine-grained diagnostics of decision failures that aggregate evaluation alone cannot reveal.

en
arXiv AI Papers

BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language Models

For efficient deployment of large language models (LLMs), methods of ultra-low-bit backbones reduce weight storage, memory traffic, and linear-layer execution cost, while multi-token prediction (MTP) methods reduce sequential decoding steps by predicting multiple future tokens in parallel. Although complementary, the direct combination of these methods cannot accelerate decoding at comparable quality: masked drafting lacks intermediate token input supplied in next-token training, while wider computation and causal key-value (KV) updates can offset the savings from fewer steps. To address these challenges, we propose BitMTP, an algorithm-system co-design framework for efficient MTP on ultra-low-bit LLM backbones. A joint next-token prediction and MTP objective equips a single model with both autoregressive (AR) generation and block-causal drafting. Confidence-only decoding, speculative-only decoding, and hybrid decoding provide different quality-throughput operating points without using separate draft and verifier models. Accepted-prefix alignment keeps the committed prefix, materialized causal KV boundary, and CUDA Graph replay state consistent for continued generation. BitMTP uses this contract to select width-specialized low-bit execution and reuse captured graphs over shared KV storage. On NVIDIA H20, BitMTP with hybrid decoding achieves five-task mean speedups of 2.2x on BitNet b1.58-2B and 2.1-2.4x on 1.7B-4B Bonsai models at comparable task quality. On RTX 3090 and Jetson Orin, it further achieves up to 2.0x in five-task mean throughput and 3.3x on MBPP+, respectively. These results demonstrate that BitMTP accelerates ultra-low-bit LLM generation across backbones, model sizes, and GPU types. The source code is released at https://github.com/PolyU-VCLab/BitMTP

en
AWS Machine Learning Blog

Discover tools at runtime with AWS Agent Registry

Hardcoded tool wiring breaks down as an agent's catalog grows from a handful of tools to hundreds. This post walks through a runtime Discover, Instantiate, Execute loop built on AWS Agent Registry, where an orchestrator discovers MCP servers and A2A agents through semantic search at runtime instead of compiling every tool at build time.

en
AWS Machine Learning Blog

Securing AI agent identity with X.509 PKI on AWS

Learn how to secure multi-agent AI systems with cryptographic identity using Keyfactor EJBCA and AWS services. This reference architecture combines signed request envelopes, user-signed delegation assertions, RFC 8693 audience-scoped tokens, and real-time OCSP revocation to prove agent identity and prevent request forgery across agent-to-agent and MCP tool calls.

en
arXiv AI Papers

Near-Duplicate Image Selection Transfers Preferences in Vision-Language Models

Subliminal learning is the phenomenon in which a model transmits its preferences to another model through data that do not explicitly express them. As models increasingly curate training data for other models, we ask whether this transfer can arise from choosing among near-duplicate images while keeping the source photographs and human-written captions fixed. For each photograph, a curator selects one of eight near-duplicate variants by caption likelihood, without target-specific prompts. Students trained on target-preferring curators' selections show higher mean target-versus-alternatives log-likelihood ratios in an image-free readout than students trained on neutral selections. Under a prespecified decision rule, this directional shift appears for an owl target in LLaVA-1.5, Qwen2.5-VL, Qwen3-VL, and Gemma 4, with curators and students initialized from the same base checkpoint, and target rotations move it toward camels, oak trees, and a political figure. The owl target-selected student also scores above all count-matched random-reselection students in three models and above 55 of 60 in LLaVA-1.5, and Qwen3-VL shows the shift again on a new source bank with newly trained curators. Its size depends on dataset size, learning rate, and training budget; greedy choices among the eight options move toward the target by 10.4 percentage points in Qwen3-VL and 0.5-1.3 points elsewhere. First-generation students also pass the owl preference to a second generation through captions without explicit owl mentions in LLaVA-1.5 and Qwen3-VL. Thus even a deduplication-style choice among near-identical copies can shift students' target-relative readouts with source photographs and captions fixed; the tested linear probes classify the selecting arm with accuracies up to 59.7% (chance 50%).

en
arXiv AI Papers

From DQI to C-DQI: Automatic Codebook Generation and Evaluation for Measuring Computational Discourse Quality Index

Effective democratic deliberation is vital for civic engagement and the health of legislative institutions. However, assessing parliamentary discourse quality is traditionally done using expert-scored, theory-based codebooks (CBs), which are rigid, labor-intensive, and prone to biases. While Large Language Models (LLMs) offer a scalable alternative for both schema induction and discourse annotation, ensuring schema quality and mitigating models' inherent bias remains a clear challenge. In this work, we propose a complete protocol for LLM-based codebook generation and evaluation. Starting from the widely accepted discourse quality Index (DQI), we compare top-down (theory-based), bottom-up (data-driven), and hybrid approaches for generating context-adapted schemas. To evaluate these schemas, we define an extrinsic proxy measure, validated by manual annotations, alongside an intrinsic inter-model agreement (IMA) metric, which leverages differing model biases to signal overall reliability. Our experiments on 100 Israeli parliament transcripts reveal that inductive, data-driven schemas achieve higher IMA than top-down methods while maintaining validity, demonstrating their potential for reliable, large-scale analysis of political discourse.

en
arXiv AI Papers

Why Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived Factors

Psycholinguistic studies explore why humans accept some generic statements but reject others by showing that these judgments depend on more than how common a property is. People consider several other factors such as how well it sets the kind apart from others or whether it is characteristic of the kind. Inspired by the linguistic and cognitive literature, we explore to what extent factors from these studies explain how large language models (LLMs) judge generics. Our results with twelve models on a psycholinguistic dataset and on naturally occurring generics show that models weigh how common a property is against how well it distinguishes the kind, and combine the two much as people do, though less clearly. Like people, they favor characteristic properties, but unlike the accounts of human judgment, they ignore striking ones. What matters most to LLMs is whether a statement is factually true, and much of the influence of human factors reaches their ratings through that judgment. In six 7-9B models, shifting the hidden states along each factor's direction moves the judgment as the factor predicts.

en
arXiv AI Papers

ACE-Compression: An Ability-Centric Evaluation of Compressed Large Language Models

Model compression makes large language models deployable, but today's evaluation tells an incomplete story. Standard practice measures retained task performance and stops there. This misses a critical fact: compression perturbs the distributed knowledge embedded across billions of weights, and task scores alone cannot reveal which underlying abilities survive and which quietly collapse. To solve this question, we introduce ACE-Compression, an ability-centric evaluation framework. Instead of asking only "does the compressed model still answer correctly?", we ask "which of its core abilities remain intact?" Our framework probes four deployment-facing dimensions: procedural reasoning and constraint execution, knowledge grounding and truthfulness, social cognition and affective understanding, and persona fidelity and stylistic consistency. Across more than 35 compressed checkpoints from six open-weight LLMs-covering quantization and pruning-we find that compression redistributes ability profiles. Coarse, local, and surface-level signals often persist, while fine-grained, long-tail, and context-dependent abilities become fragile. Quantization consistently outperforms pruning in retention, but the practical meaning of that gap depends entirely on which ability an application requires. Based on our findings, deployers can choose compression methods by the ability profile their application needs, not just by a leaderboard average. And algorithm designers gain diagnostic signals to build compression methods that preserve what matters. We believe that ACE-Compression turns compression from a black-box accuracy drop into an interpretable intervention-one we can measure, understand, and ultimately improve.

en
arXiv AI Papers

Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial Framing

Negation remains a persistent challenge for language models across NLP tasks and modalities. We show that this weakness can undermine LLM safety guardrails through a structural vulnerability we term polarity blindness: the failure to recognize harmful intent after polarity-altering linguistic transformations. We study two forms of polarity inversion: grammatical negation and antonym replacement, and use synonym replacement as a polarity-preserving control. We further test whether an adversarial textual wrapper amplifies these failures. Using a 260-prompt benchmark across 10 state-of-the-art LLMs and 3 languages (English, Spanish, Czech), stratified by harmfulness potential and evaluated on a validated 0-5 harm scale, we find that polarity blindness affects most evaluated models, with mean harm scores reaching 4.12 for the most vulnerable model. The effect persists across typologically differing negation systems, suggesting that polarity blindness reflects a broader limitation in semantic robustness rather than a language- or grammar-specific failure.

en
arXiv AI Papers

CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward Decomposition

Large Language Models (LLMs) are increasingly used as research collaborators for hypothesis refinement, methodological planning, and technical analysis across multi-turn interactions. In this setting, a useful assistant must be accurate, methodologically justified, logically consistent, and token-efficient. Current alignment approaches rarely achieve all of these together. Instruction-tuned models gain conversational quality through verbosity, and we show that science-agnostic general collaborative rewards compress responses at the expense of scientific rigor. We propose CollabSciReM, a goal-conditioned reward framework that decomposes the session-level reward into conversational quality, scientific rigor, and structural efficiency. We also introduce SciQuality, a pairwise evaluation of multi-turn research conversations grounded in 300 held-out scientific papers and scored on six dimensions: methodological soundness, justification, logical consistency, factual correctness, novelty, and responsiveness. Fine-tuned on 8.62K synthetic research conversations, CollabSciReM is preferred on SciQuality over a science-agnostic reward baseline trained on the same data for all four Llama and Qwen models, including a 65.3% win rate at matched response length. For the 7B and 8B models, CollabSciReM outperforms the science-agnostic reward baseline on the primary metric in 8 of 10 single- and multi-turn benchmark settings. In a blind study, domain experts rated CollabSciReM significantly higher on novelty than the general-reward variant and reported fewer hallucinated responses than both the general-reward variant and the base model.

en
arXiv AI Papers

The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer It

Direct preference optimisation (DPO) is widely used for language model post-training, but its performance depends strongly on the choice of its hyperparameters, such as the learning rate and the reference-policy regularisation parameter β. To better understand the DPO hyperparameter landscape, we conduct extensive experiments using a dense hyperparameter grid across different model scales from the same family. This allows us to analyse how the optimal DPO hyperparameters evolve with model size and the number of update steps, with intermediate checkpoints providing an inexpensive signal to accelerate the hyperparameter optimisation process. Furthermore, by evaluating our models on both static and dynamic benchmarks, we identify which benchmarks provide the strongest signal for hyperparameter selection. Finally, we investigate how different state-of-the-art hyperparameter optimisation strategies perform in this setting. Our experiments show that the optimal learning rate varies with model size and that hyperparameters are not transferable across training datasets. We also find that validation loss is a poor proxy for hyperparameter optimisation, as hyperparameters that minimize validation loss only weakly correlate with optimal hyperparameters for downstream benchmarks. Therefore, DPO hyperparameters need to be tuned specifically for the target model, dataset, and evaluation objective. We also show that short candidate training runs can substantially reduce the cost of this selection. We release all our training configurations and evaluation results to support reproducible analysis of selection quality and training cost.

en
arXiv AI Papers

Testing Associative Creativity in Humans and Multimodal LLMs with Difficult-to-Name Visual Stimuli

We investigate associative creativity in descriptions of abstract visual stimuli by humans and multimodal large language models (MLLMs). While conceptual association is central to human communication, it remains unclear how humans and models adapt when visual stimuli become increasingly difficult to map onto familiar semantic concepts. We evaluate several state-of-the-art MLLMs and human participants along two dimensions of creativity, originality and effectiveness, using two datasets with controlled manipulations of difficulty. SilCC varies naming difficulty through progressively more complex combinations of abstract shapes, and PixCC varies difficulty through increasing levels of random visual noise. Results show that humans produce more diverse associative descriptions than MLLMs, including greater semantic distance, higher entropy, and more novel expressions relative to reference lexica. As difficulty increases, effectiveness declines in SilCC, and humans increasingly shift from holistic associations to descriptions of low-level visual properties in PixCC.

en
arXiv AI Papers

Elicitation or Expansion? Demystifying Gains from Agent Harness Optimization

Recent studies in harness optimization have shown substantial performance gains in language model agents without updating model weights. A well-designed harness more effectively leverages the underlying model's capabilities by shaping context, tool use, and execution workflows. However, naïve success rates alone do not fully characterize whether optimized harness yields more reliable success on tasks already within reach (elicitation) or a broader range of solvable tasks (expansion). This distinction is crucial for recursive self-improvement and evolutionary search, as expansion may provide a broader range of successful experiences to push the capability boundaries. Despite the growing significance, this distinction remains underexplored in harness optimization. We conduct a systematic analysis to study the effect of gains from harness optimization. Building on pass@k analyses in the reinforcement learning (RL) literature that compare models before and after RL training, we compare optimized harnesses with their pre-optimization counterparts. Specifically, we assess changes in reachable task coverage, compare harness optimization with model scaling and increased inference-time compute, and examine how gains vary with task difficulty. Across static prediction and dynamic tasks, we find that pass@1 advantages of harness over stronger interventions can reverse at larger attempt budgets and aggregate gains conceal shortfalls on hard tasks, underscoring the need for a fine-grained diagnosis.

en
arXiv AI Papers

Hallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and Mitigation

Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved code translation, their outputs still contain hallucinations: generated code that conflicts with the source program, violates target-language facts, or introduces contextually inconsistent dependencies. These failures are especially harmful in translation because small semantic deviations can silently change program behavior. Existing hallucination studies mainly focus on natural-language generation or code generation, leaving the forms, distribution, and mitigation of hallucinations in cross-language code translation insufficiently characterized. This paper presents a systematic empirical study of LLM hallucinations in code translation. Across three benchmark datasets, six language pairs, and seven LLMs, we construct a taxonomy with three major categories: Semantic Consistency Conflicts, Factual Knowledge Conflicts, and Project Context Deviations. We manually annotate 13,919 hallucination cases and analyze how hallucination types vary across models, datasets, and language directions. Guided by the taxonomy, we further propose HaluCodeTran, a mitigation framework that combines BM25-based retrieval of relevant translation examples with taxonomy-aware reflective refinement. The study provides an execution-tested characterization of code-translation hallucinations and a practical baseline for building more reliable LLM-based code migration tools.

en
arXiv AI Papers

VISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASR

Prompt-based contextual ASR requires selecting a compact hotword subset from large dynamic inventories, yet existing pre-selection methods rely either on discrete ASR hypotheses that may discard acoustic evidence or on separately trained retrieval models. We propose Viterbi-guided Selection of Hotwords (VISH), a training-free, plug-and-play framework that directly verifies candidate-specific acoustic support over frame-level CTC posteriors. VISH formulates pre-selection as constrained posterior search; M-VISH makes large-list verification scalable through frame-synchronous shared-prefix Viterbi search with bounded top-K pruning, while Bi-MVISH exploits complementary backward evidence for robust verification. Across five benchmarks, M-VISH achieves up to 11.7% absolute improvement in Best-F1 over a strong learned-retrieval baseline and reduces candidate-search latency by 75.2% at 2,000 candidates relative to hypothesis-based filtering. These results demonstrate the effectiveness of posterior-level verification for accurate and scalable hotword pre-selection without additional model training.

en
arXiv AI Papers

From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved Code

The increasing use of large language models for code generation calls for methods that distinguish purely human-written code from AI-involved code: files in which any part, however small, was generated or substantially modified by a model. Beyond flagging such files, we aim to localize the lines or blocks attributable to AI. Existing approaches compress a file into a single score, from surface stylistic features or a global code representation, which averages away the evidence when only a few blocks are AI-involved. We propose a framework that models AI authorship at the token level and predicts at the line, block, and file levels. A frozen code language model is equipped with two low-rank adapters, trained separately on machine-written and human-written files; their per-token log-likelihood ratio provides local evidence of AI authorship. Lightweight heads aggregate this evidence within lines and blocks, using the surrounding code context, and their local predictions are aggregated into a file-level decision. We train on mixed-authorship files built from human originals and their AI-generated or AI-modified counterparts, including continuation and fill-in-the-middle scenarios. On an internal test set of 11,773 AI-involved files across six generation regimes against 2,541 human files, our method reaches 72.4 macro F1 at a 1% FPR operating point. With no adaptation, it reaches 62.5 line-level F1 on HybridCodeAuthorship, an external human-AI co-writing benchmark with no training split, above the 56 its own paper reports as the best line-level result. On 19,445 human-written files from repositories created before 2022, the false-positive rate stays between 0.55% and 0.81% under the transported 1% threshold, so the operating point holds on real human code.

en