arXiv AI
Jun 30
Latent Bridges for Multi-Table Question Answering
arXiv:2606. 28916v1 Announce Type: cross Abstract: We introduce GRAB, a constructor-encoder-bridge pipeline for table question answering.
Can LLMs Use Relational Transformer Embeddings?
The paper investigates whether large language models (LLMs) can leverage frozen relational‑transformer embeddings by injecting them as soft tokens. Using a learned MLP projection and LoRA adaptation, the authors fine‑tune Qwen3.5‑4B on chain‑of‑thought reasoning traces and group‑based reinforcement learning, then evaluate on ten binary classification tasks across six RelBench databases. The hybrid approach consistently underperforms the standalone relational transformer, showing sensitivity to serialization format, token budget, and RL stability, leading the authors to conclude that stronger alignment objectives and schema‑aware design are needed for reliable relational prediction.
Related stories
Hugging Face Trending Papers
Oct 16
Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations
Prior-data fitted networks (PFNs) show that pretraining on large populations of synthetic tasks can enable generalization to unseen datasets with little or no downstream fine-tuning. This paradigm is...
arXiv AI
Oct 19
Path to Prior-Data Fitted Relational Models via Learned Latent Multi-table Representations
The paper investigates whether prior‑data‑fitted networks (PFNs) can be extended to graph‑based relational models. The authors pretrain a message‑passing foundation model, Griffin, on large synthetic relational databases and evaluate its frozen encoder on 16 real‑world relational classification tasks. A curriculum that starts with schema‑guided synthetic data and then uses schema‑agnostic data yields the best in‑context performance, outperforming real‑data‑only pretraining and other mixtures.
arXiv Machine Learning
Jun 30
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
arXiv:2606. 30336v1 Announce Type: new Abstract: We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders.
Hugging Face Trending Papers
Jun 29
FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
We introduce FlexTab, a flexible encoder-decoder architecture for in-context learning on tabular data that pairs a single, task-agnostic encoder with a suite of task-specific decoders. Unlike existing tabular in-context learners, which entangle feature representations with a specific prediction target, our design produces \textit{target-agnostic} row embeddings that can be leveraged across a wide range of downstream tasks within a table-native in-context learning setup.
arXiv Computation and Language
Sep 25
CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models
CONSISTRE is a consistency‑aware framework for document‑level relation extraction that tackles contradictions in large language model predictions. It offers two tracks: an inference‑time track that refines black‑box LLM outputs through constraint‑aware prompting, verification, and self‑reflection, and a training‑time track that distills consistency knowledge into smaller open‑source models via supervised fine‑tuning and reinforcement learning. Experiments on DocRED show both tracks outperform baselines, with the inference‑time track matching competitive F1 scores and the training‑time track narrowing the performance gap to proprietary LLMs while reducing inference cost.
arXiv AI
Jul 2
Predicting LLM Reasoning Performance with Small Proxy Model
arXiv:2509. 21013v4 Announce Type: replace-cross Abstract: Given the prohibitive cost of pre-training large language models, it is essential to leverage smaller proxy models to optimize datasets before scaling up.
arXiv AI
Jul 21
Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning
arXiv:2505. 20161v2 Announce Type: replace-cross Abstract: Effective generalization in language models depends critically on the diversity of their training data.
arXiv AI
Jun 16
AdaMame: A Training Recipe for Adaptive Multilingual Reasoning
arXiv:2606. 15080v1 Announce Type: cross Abstract: While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known as language collapse.
Hugging Face Trending Papers
Jul 27
CONSISTRE: A Unified Consistency-Aware Framework for Document-Level Relation Extraction with Large Language Models
Document-level relation extraction (DocRE) aims to extract relations among multiple entities across extended contexts while maintaining consistency across predicted triples. Although large language models (LLMs) show remarkable reasoning capabilities in information extraction, their predictions are typically generated independently for each candidate triple and may violate fundamental relational constraints such as transitivity, symmetry, and functional uniqueness, leading to contradictory and unreliable outputs.
arXiv Machine Learning
Oct 22
RelAgent: LLM Agents as Data Scientists for Relational Learning
RelAgent is an LLM-based autonomous data scientist designed for relational learning. It operates in two phases: first, the LLM agent constructs SQL feature programs and selects a predictive model using database, validation, and evaluation tools; second, the resulting program is executed without further LLM calls. The final predictor combines SQL queries and a classical model, providing fast, deterministic, and interpretable predictions that rely solely on human-readable query-defined features.
arXiv AI
Oct 21
CHIMERA: Compact Synthetic Data for Generalizable LLM Reasoning
arXiv:2603.00889v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, largely enabled by supervised fine-tuning (SFT)- and reinforce...