World PulseNow
Newsletter

Preference is More Than Comparisons: Rethinking Dueling Bandits with Augmented Human Feedback

arXiv — cs.LG•Thursday, November 13, 2025 at 5:00:00 AM
PositiveArtificial Intelligence
The recent study on interactive preference elicitation (IPE) highlights the limitations of traditional dueling bandit (DB) algorithms, particularly their inefficiency in scenarios with sparse human feedback. Existing methods often depend on rigid parametric reward models, which can lead to inaccuracies. In response, the researchers propose a novel approach that incorporates augmented human feedback, leading to the development of a prototype algorithm that shows competitive performance across multiple IPE benchmarks. This advancement not only addresses the shortcomings of current methods but also opens up new possibilities for efficient decision-making in personalization systems, such as recommendations and multi-objective optimization. The findings underscore the importance of evolving algorithms to better harness human input, ultimately enhancing user experiences in various applications.
— via World Pulse Now AI Editorial System
Read Original

Was this article worth reading? Share it

Recommended Readings
Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
arXiv — cs.CL2 hours ago
Towards Alignment-Centric Paradigm: A Survey of Instruction Tuning in Large Language Models
PositiveArtificial Intelligence
Instruction tuning is a crucial method for aligning large language models (LLMs) with human intentions and safety requirements. This survey outlines the entire process, including data collection methods, fine-tuning strategies, and evaluation protocols. It categorizes data construction into expert annotation, distillation from larger models, and self-improvement mechanisms, each with unique trade-offs. The study also addresses challenges in evaluating model performance across multilingual and multimodal contexts.
Read full article
via arXiv — cs.CL
Bias after Prompting: Persistent Discrimination in Large Language Models
arXiv — cs.CL2 hours ago
Bias after Prompting: Persistent Discrimination in Large Language Models
NegativeArtificial Intelligence
A recent study challenges the assumption that biases do not transfer from pre-trained large language models (LLMs) to adapted models. The research indicates that biases can persist through prompting, a common adaptation strategy, with strong correlations observed across demographics such as gender, age, and religion. This finding raises concerns about the effectiveness of current bias mitigation methods in LLMs.
Read full article
via arXiv — cs.CL
LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
arXiv — cs.CL2 hours ago
LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
PositiveArtificial Intelligence
LiveCLKTBench is an automated generation pipeline designed to evaluate cross-lingual knowledge transfer in large language models (LLMs). It isolates and measures knowledge transfer by identifying time-sensitive knowledge entities, filtering them based on temporal occurrence, and generating factual questions translated into multiple languages. The evaluation of several LLMs across five languages reveals that cross-lingual transfer is influenced by linguistic distance and is often asymmetric.
Read full article
via arXiv — cs.CL
FlakyGuard: Automatically Fixing Flaky Tests at Industry Scale
arXiv — cs.LGa day ago
FlakyGuard: Automatically Fixing Flaky Tests at Industry Scale
PositiveArtificial Intelligence
Flaky tests, which unpredictably pass or fail, hinder developer productivity and delay software releases. FlakyGuard is introduced as a solution that leverages large language models (LLMs) to automatically repair these tests. Unlike previous methods like FlakyDoctor, FlakyGuard effectively addresses the context problem by structuring code as a graph and selectively exploring relevant contexts. Evaluation of FlakyGuard on real-world tests indicates a repair success rate of 47.6%, with 51.8% of fixes accepted by developers, marking a significant improvement over existing approaches.
Read full article
via arXiv — cs.LG
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
arXiv — cs.LGa day ago
Beat the long tail: Distribution-Aware Speculative Decoding for RL Training
PositiveArtificial Intelligence
The paper titled 'Beat the long tail: Distribution-Aware Speculative Decoding for RL Training' introduces a new framework called DAS, aimed at improving the efficiency of reinforcement learning (RL) rollouts for large language models (LLMs). The study identifies a bottleneck in the rollout phase, where long trajectories consume significant time. DAS employs an adaptive drafter and a length-aware speculation policy to optimize the rollout process without changing model outputs, enhancing the overall training efficiency.
Read full article
via arXiv — cs.LG
Failure to Mix: Large language models struggle to answer according to desired probability distributions
arXiv — cs.LGa day ago
Failure to Mix: Large language models struggle to answer according to desired probability distributions
NegativeArtificial Intelligence
Recent research indicates that large language models (LLMs) struggle to generate outputs that align with specified probability distributions. Experiments revealed that when asked to produce binary outputs with a target probability, LLMs consistently failed to meet these expectations, often defaulting to the most probable answer. This behavior undermines the probabilistic exploration necessary for scientific idea generation and selection, raising concerns about the effectiveness of current AI training methodologies.
Read full article
via arXiv — cs.LG
GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification
arXiv — cs.CVa day ago
GMAT: Grounded Multi-Agent Clinical Description Generation for Text Encoder in Vision-Language MIL for Whole Slide Image Classification
PositiveArtificial Intelligence
The article presents a new framework called GMAT, which enhances Multiple Instance Learning (MIL) for whole slide image (WSI) classification. By integrating vision-language models (VLMs), GMAT aims to improve the generation of clinical descriptions that are more expressive and medically specific. This addresses limitations in existing methods that rely on large language models (LLMs) for generating descriptions, which often lack domain grounding and detailed medical specificity, thus improving alignment with visual features.
Read full article
via arXiv — cs.CV
DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning
arXiv — cs.CLa day ago
DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning
PositiveArtificial Intelligence
DataSage is a novel multi-agent framework designed to enhance insight discovery in data analytics. It addresses limitations of existing data insight agents by incorporating external knowledge retrieval, a multi-role debating mechanism, and multi-path reasoning. These features aim to improve the depth of analysis and the accuracy of insights generated, thereby assisting organizations in making informed decisions in a data-driven environment.
Read full article
via arXiv — cs.CL