Classical and neural NLP: translation, question answering, tokenization and the evaluation of language understanding.
arXiv:2606. 26487v1 Announce Type: cross Abstract: Large language models (LLMs) are attractive for context-aware time series forecasting because they can integrate heterogeneous textual signals, yet their discrete, language-oriented tokenization and embedding interfaces are misaligned with continuous numerical values, often harming numerical ordering and forecasting reliability.
Verifying the eligibility of securities as collateral is a key responsibility of the German Central Bank. However, manually verifying these assets against legal and financial criteria within lengthy, semi-structured, and often bilingual prospectuses is a resource-intensive task.
Translation cascades for reasoning translate the query from another language to English, reason in English, and translate the answer back to the original language. This is a competitive approach to multilingual reasoning, but structurally lossy, since each stage discards information later stages may need, including cues for cultural grounding, register, and disambiguation.
Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, lexical metrics correlate poorly with human judgments on open-ended generation, and holistic LLM judges often produce opaque scores that are hard to debug. We propose BINEVAL, a framework that decomposes evaluation criteria into atomic binary questions and aggregates the resulting verdicts into interpretable, multi-dimensional scores.
Kolmogorov Arnold networks (KAN) have recently been introduced as a (deep) neural network architecture whose trainable parameters adapt the activation functions, instead of the coefficients of the affine transformations at the core of traditional architectures such as deep multilayer perceptrons (MLPs). This architecture builds on the Kolmogorov-Arnold theorem, which endows it with universal approximation properties.
Multi-task model merging aims to consolidate several task-specific experts into a unified model, yet static merging consistently suffers from parameter interference. While dynamic merging models aim to bridge this gap, many works rely on the costly storage and loading of redundant expert components at inference.
arXiv:2405. 01741v4 Announce Type: replace-cross Abstract: Reliability of AI systems is a fundamental concern for the successful deployment and widespread adoption of AI technologies.
arXiv:2606. 25147v1 Announce Type: cross Abstract: User modeling in industrial recommender systems typically produces dense embeddings, which suffer from representational constraints inherent to fixed-dimensional vectors.
arXiv:2606. 25519v1 Announce Type: cross Abstract: Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-answer accuracy or per-token latency.
arXiv:2605. 31220v2 Announce Type: replace-cross Abstract: Confidence estimation (CE), i.
arXiv:2606. 25987v1 Announce Type: cross Abstract: Large language models (LLMs) attain remarkable surface fluency on code, yet they neither formally guarantee the syntactic validity of their output nor leverage the hierarchical structure defining the target language.
While corporate narrative disclosures provide crucial information to capital markets, comprehensively evaluating their qualitative changes over time remains challenging. Narrative text is inherently multidimensional, meaning that an improvement in one textual dimension often occurs alongside changes in others.
Was this person ever at that place, and if so, when? Answering such questions from noisy, multilingual historical documents is the central challenge of HIPE-2026, the third edition of the HIPE evaluation series.
We introduce SurgAtlas, the largest surgical video-language dataset to date, comprising 15,291 videos (2,391 hours) spanning 18 surgical specialties and over 5,000 procedure types, sourced entirely from publicly available YouTube content. SurgAtlas is also the first surgical video-language dataset to include open surgery at scale, with 6,182 open procedure videos alongside over 9,000 minimally invasive recordings, and the first to establish standardized benchmarks for open-surgery video understanding.
When people share experiences online, they often express thoughts in two ways: a star rating and a written review. In sentiment analysis, ratings are widely used as convenient weak labels for textual sentiment, yet whether the two actually agree is rarely questioned.
Recent Large Audio Language Models (LALMs) have achieved remarkable progress in audio perceptual tasks across individual acoustic layers, including speech, sound, and music. However, existing benchmarks predominantly evaluate these layers in isolation, overlooking the complex contextual relationships that arise when multiple acoustic sources co-occur in real-world auditory scenes.
arXiv:2601. 04524v2 Announce Type: replace Abstract: Understanding biomedical experiments provides a foundation for downstream tasks, e.
arXiv:2606. 24172v1 Announce Type: cross Abstract: More than a billion people communicate in Indic languages, yet the natural language processing infrastructure serving them remains fragmented and underdeveloped.
arXiv:2507. 09839v2 Announce Type: replace Abstract: An increasing number of NLP applications interact with large language models (LLMs) through black-box APIs, making prompt engineering critical for controlling model behavior.
arXiv:2606. 23942v1 Announce Type: new Abstract: We present a large-scale empirical study isolating the contributions of the Derivative Regularization penalty (DREG).