Beyond Semantics: How Temporal Biases Shape Retrieval in Transformer and State-Space Models

arXiv — cs.CL•Tuesday, October 28, 2025 at 4:00:00 AM

A recent study explores how temporal biases influence the retrieval capabilities of various large language models, including transformer and state-space models. By drawing parallels to human episodic memory, the research highlights the importance of distinguishing between events that occur at different times. This understanding is crucial as it can enhance the performance of language models in retrieving contextual information, ultimately improving their effectiveness in real-world applications.

— via World Pulse Now AI Editorial System

Read Original

Was this article worth reading? Share it

LucidQuery AI

Combines diffusion reasoning with autoregressive LLM for advanced AI analysis.

AI & DataView app details

Airparser

Extract and parse data from documents using GPT-4 automation.

AI & DataView app details

Supametas.AI

Extract and structure unstructured data for seamless LLM RAG integration.

AI & DataView app details

Continue Readings

arXiv — cs.CL2 days ago

QSTN: A Modular Framework for Robust Questionnaire Inference with Large Language Models

PositiveArtificial Intelligence

QSTN has been introduced as an open-source Python framework designed to generate responses from questionnaire-style prompts, facilitating in-silico surveys and annotation tasks with large language models (LLMs). The framework allows for robust evaluation of questionnaire presentation and response generation methods, based on an extensive analysis of over 40 million survey responses.

Read full article

via arXiv — cs.CL

arXiv — cs.LG2 days ago

Provably Mitigating Corruption, Overoptimization, and Verbosity Simultaneously in Offline and Online RLHF/DPO Alignment

PositiveArtificial Intelligence

A new study introduces RLHF-COV and DPO-COV algorithms designed to address critical issues in reinforcement learning from human feedback (RLHF) and direct preference optimization (DPO), specifically targeting corrupted preferences, reward overoptimization, and verbosity in large language models (LLMs). These algorithms promise to enhance the alignment of LLMs with human preferences in both offline and online settings.

Read full article

via arXiv — cs.LG

arXiv — cs.CL2 days ago

What Triggers my Model? Contrastive Explanations Inform Gender Choices by Translation Models

NeutralArtificial Intelligence

A recent study published on arXiv explores the interpretability of machine translation models, particularly focusing on how gender bias manifests in translation choices. By utilizing contrastive explanations and saliency attribution, the research investigates the influence of context, specifically input tokens, on the gender inflection selected by translation models. This approach aims to uncover the origins of gender bias rather than merely measuring its presence.

Read full article

via arXiv — cs.CL

arXiv — cs.CL2 days ago

Soft Inductive Bias Approach via Explicit Reasoning Perspectives in Inappropriate Utterance Detection Using Large Language Models

PositiveArtificial Intelligence

A new study has introduced a soft inductive bias approach to enhance inappropriate utterance detection in conversational texts using large language models (LLMs), specifically focusing on Korean corpora. This method aims to define explicit reasoning perspectives to guide inference processes, thereby improving rational decision-making and reducing errors in detecting inappropriate remarks.

Read full article

via arXiv — cs.CL

arXiv — cs.LG2 days ago

Balanced Accuracy: The Right Metric for Evaluating LLM Judges - Explained through Youden's J statistic

NeutralArtificial Intelligence

The evaluation of large language models (LLMs) is increasingly reliant on classifiers, either LLMs or human annotators, to assess desirable or undesirable behaviors. A recent study highlights that traditional metrics like Accuracy and F1 can be misleading due to class imbalances, advocating for the use of Youden's J statistic and Balanced Accuracy as more reliable alternatives for selecting evaluators.

Read full article

via arXiv — cs.LG

arXiv — cs.LG2 days ago

Biothreat Benchmark Generation Framework for Evaluating Frontier AI Models II: Benchmark Generation Process

NeutralArtificial Intelligence

The Biothreat Benchmark Generation Framework has introduced the Bacterial Biothreat Benchmark (B3) dataset, aimed at evaluating the biosecurity risks associated with frontier AI models, particularly large language models (LLMs). This framework employs web-based prompt generation, red teaming, and mining existing benchmark corpora to create over 7,000 potential benchmarks linked to the Task-Query Architecture.

Read full article

via arXiv — cs.LG

arXiv — cs.CL2 days ago

Short-Context Dominance: How Much Local Context Natural Language Actually Needs?

NeutralArtificial Intelligence

The study investigates the short-context dominance hypothesis, suggesting that a small local prefix can often predict the next tokens in sequences. Using large language models, researchers found that 75-80% of sequences from long-context documents only require the last 96 tokens for accurate predictions, leading to the introduction of a new metric called Distributionally Aware MCL (DaMCL) to identify challenging long-context sequences.

Read full article

via arXiv — cs.CL

arXiv — cs.LG2 days ago

OMNIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities

PositiveArtificial Intelligence

The introduction of Omniguard presents a novel approach to AI safety moderation by enhancing the detection of harmful prompts across various languages and modalities, addressing the vulnerabilities of large language models (LLMs) to misuse. This method improves classification accuracy by 11.57% over existing baselines, marking a significant advancement in AI safety protocols.

Read full article

via arXiv — cs.LG