Research Feed

CritICL improves large language model performance by providing targeted, failure-aware critique examples in the prompt to steer reasoning away from common pitfalls.

TTPO improves the reasoning accuracy of language models during test time by using label-free policy optimization that bypasses the need for manual ground-truth data.

The authors introduce VBVR-Pro, a suite designed to improve visual reasoning capabilities in models by using verifiable generative tasks.

FedV-KGQA enables multi-hop reasoning over knowledge graphs distributed across different organizations by fusing local entity embeddings without sharing private raw data.

The paper introduces a constraint-based verification method that filters LLM responses against knowledge graph logic to significantly improve answer precision without sacrificing recall.

PARTAB improves table-based reasoning by decomposing tables into semantically coherent parts before processing them with a multi-stage pipeline.

The paper introduces a method called OPDVR that aligns reinforcement learning signal with task success during model distillation to improve reasoning performance.

Selective Regenerative Decoding optimizes LLM inference by identifying and regenerating only the degraded portions of a reasoning sequence rather than discarding the entire trajectory.

The researchers introduce a penalty method to prevent language models from sacrificing safety protocols when they are fine-tuned for improved reasoning tasks.

The authors created the ICU-REACT dataset and a corresponding family of fine-tuned models to improve LLM performance in identifying and reasoning over patient data for critical care.

The paper introduces StrategyBench to evaluate if language models can effectively derive and apply explicit task-level strategies from few-shot examples.

The paper introduces a framework called DynaRule that enables large language models to dynamically retrieve and apply reusable procedural rules at scale.

The paper introduces a method that improves the efficiency and accuracy of chain of thought reasoning by injecting relevant, pre-computed reasoning patterns into the model prompt.

This study demonstrates that LLM judges struggle to separate content accuracy from source reliability, showing higher trust and accuracy scores when content is attributed to humans compared to AI.

EnSI-RAG improves long-document question answering by indexing documents based on structured entity relationships rather than simple text chunks.

A single researcher successfully used AI agents to develop a complete system from application code to silicon tapeout in five weeks.

The researchers developed an LLM that uses Reinforcement Learning Fine-Tuning and specialized rewards to improve performance in single-step retrosynthesis tasks.

Researchers developed a method to extract near-verbatim chain-of-thought reasoning traces from black-box reasoning models using adversarial API injection techniques.

Researchers evaluated how large language models weigh conflicting evidence, finding they often over-rely on numerical data and external tool forecasts.

The paper introduces a training-free inference-time protocol that uses a self-critique loop and a confirmed sentinel to improve reasoning accuracy while early-stopping redundant computations.