arxiv arXiv cs.CL · 7h ago

EVLA: An Electro-Aware Multimodal Assistant for Physically-Grounded Driving Reasoning and Control

The authors introduce the Electro-Visual-Language Assistant (EVLA), a framework that integrates multi-modal scene understanding with real-time perception of an electrified powertrain's electro-mechanical state to improve driving decisions. This approach addresses the limitation of existing vision-language models that treat vehicle dynamics as a black box by incorporating physical constraints and optimization objectives.

arxiv arXiv cs.CL · 7h ago

A3M: Adaptive, Adversarial and Multi-Objective Learning for Strategic Bidding in Repeated Auctions

The A3M framework addresses the challenges of learning to bid in repeated multi-unit auctions by integrating adaptive deep reinforcement learning, adversarial reasoning, and multi-objective reward design. It utilizes an actor-critic backbone and opponent modeling to optimize strategy against non-stationary adversaries while balancing utility, revenue, and fairness.

arxiv arXiv cs.CL · 7h ago

Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

This paper proposes a filtering defense against dirty-label poisoning attacks on speech commands classification systems by clustering unsupervised representations to identify and remove poisoned training data.

arxiv arXiv cs.CL · 7h ago

Beyond the Mean: Three-Axis Fidelity for Aligning LLM-Based Survey Simulators from Small Pilot Data

This study investigates whether large language models can recover the statistical characteristics of a broader population using only a small pilot sample of human responses. The authors decompose this recovery into three axes: structural fidelity, marginal fidelity, and individual fidelity.

arxiv arXiv cs.CL · 7h ago

Can LLMs Hire Fairly? Racial Bias in Resume Screening

An audit of fourteen mainstream large language models reveals a significant shift in racial bias within resume screening algorithms over recent years. While 2023-vintage models reproduce pro-White callback gaps, all models released in 2024 or later show either null gaps or significant pro-Black reversals.

arxiv arXiv cs.CL · 7h ago

AgriTune-R: A Reproducible Framework for Fine-Tuning LLMs in Agriculture

The paper introduces AgriTune-R, a reproducible and auditable framework designed to adapt general-purpose large language models for specific agricultural applications. This approach addresses the domain-specific, safety-critical nature of agriculture by integrating data governance, expert evaluation, and evidence constraints to prevent unreliable advice.

arxiv arXiv cs.CL · 7h ago

BERTomelo: Your Portuguese Encoder Best Friend

This article introduces BERTomelo, a next-generation monolingual encoder specifically optimized for the Portuguese language using the ModernBERT architecture.

arxiv arXiv cs.CL · 7h ago

Conversational Domain Adaptation of IndicTrans2 via Experience Replay and Model Soups

The authors adapt the open-source IndicTrans2-1B translation system to handle conversational register across 21 Indic languages using only public datasets. By combining experience replay with model souping, they achieve significant improvements in automatic metrics without degrading performance on general domain tasks.

arxiv arXiv cs.CL · 7h ago

Clinical Evidence Strength Is Recoverable From LLM Representations, Not Stated Grades

A study of 22 open-weight large language models reveals that while the strength of clinical evidence can be recovered from model activations and text, the grades explicitly stated by the models are no better than chance. Researchers analyzed 45,134 clinical claims harmonized into four-level evidence grades to test whether models register and express evidence strength distinct from factual truth.

arxiv arXiv cs.CL · 7h ago

How to Leverage Synthetic Speech for LLM-Based ASR Systems?

Researchers investigate the distributional gap between synthetic and real speech in LLM-based automatic speech recognition (ASR) systems by probing a SLAM-ASR architecture. They identify that discriminative signals separating the two data types are concentrated in the early-to-middle layers of the model backbone.

arxiv arXiv cs.CL · 7h ago

Masked Diffusion Decoding as x-Prediction Flow

This paper introduces a continuous decoding framework for masked diffusion language models (MDLMs) that reinterprets mask prediction as clean-state prediction to induce a continuous flow in input embedding space. By allowing tokens to accumulate partial progress and remain revisable, the method addresses the premature commitments inherent in standard binary unmasking regimes.

arxiv arXiv cs.CL · 7h ago

ThinkProbe: Structural Profiling of LLM Reasoning via Non-Generative Thought Graphs

ThinkProbe is a framework for the structural analysis of large language model reasoning traces, converting them into directed Thought Graphs with eight node types and six edge types. It derives a 19-metric five-dimensional cognitive profile through a fully non-generative pipeline combining rule-based segmentation and discriminative semantic linking.

arxiv arXiv cs.CL · 7h ago

A Comparative Study on Affective Cues in Text Embeddings Across Psychological Emotion Theories

This study investigates the extent to which modern text encoders capture psychological theories of affect by evaluating twelve recently released models across three established emotion frameworks. The research compares word-level and sentence-level performance using both regression and classification tasks.

arxiv arXiv cs.CL · 7h ago

Low-cost concept-based localized explanations: How far can we get with training-free approaches?

This study evaluates whether mid-scale Multimodal Large Language Models (MLLMs) can perform localized concept naming under strict zero-shot conditions by assigning labels to bounding-box regions. The authors propose a reproducible evaluation protocol for Concept Naming that includes closed-set prompting and an embedding-similarity-based strategy for large label spaces.

arxiv arXiv cs.CL · 7h ago

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

Researchers introduce Evolution Fine-Tuning (EFT), a mid-training paradigm that teaches Large Language Models to evolve solutions across diverse tasks by converting evolutionary search trajectories into supervision. This approach addresses the limitation of prior methods that discard accumulated experience, enabling models to reuse discovery capabilities rather than solving new problems from scratch.

arxiv arXiv cs.CL · 7h ago

AB-RAG: Adaptive Budgeted Retrieval-Augmented Generation for Reliable Question Answering

AB-RAG is a training-free, backbone-agnostic framework that dynamically adjusts retrieval efforts based on a confidence estimate derived from model certainty, answer-evidence agreement, and retrieval score variance. This approach allows systems to decide whether to stop or retrieve more evidence within a fixed budget without retraining the underlying language model.

arxiv arXiv cs.CL · 7h ago

Representational Depth of Evaluation Awareness Shifts With Scale in Open-Weight Language Models

This study investigates whether language models recognize when they are being tested, a factor critical for AI safety as it may cause models to alter their behavior strategically. Using 11 open-weight models from the Qwen 2.5, Gemma 2, and Llama 3.2 families, researchers analyzed how evaluation awareness manifests across different model sizes.

arxiv arXiv cs.CL · 8h ago

Pre-Registered Screening Rule for Evolutionary Outer Loops

The authors introduce a pre-registered screening rule that determines before implementation whether an evolutionary outer loop over neural network parameters is worth building compared to a cheap single-shot alternative. The rule calculates a recovery metric R, defined as the best single-shot gain divided by the best gain of any cheap method, and prescribes skipping the outer loop when R is greater than or equal to 90%.

arxiv arXiv cs.CL · 8h ago

How Anthropomorphic Language Impacts Public Perceptions of AI

A study involving 815 participants examined whether using human-like language to describe artificial intelligence alters public perception compared to neutral descriptions.

arxiv arXiv cs.CL · 8h ago

DistilledGemma: Balanced Efficiency-Accuracy for Person-Place Relation Extraction

The authors present DistilledGemma, an efficient system for person-place relation extraction from multilingual historical newspaper articles in English, German, and French. The approach utilizes a three-stage knowledge distillation pipeline to balance classification accuracy with computational efficiency.