The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

The paper introduces CoRP, a gradient-free operator that consolidates the benefits of ensemble-based post-training methods into a single, deployable model update, significantly improving performance w…

The paper introduces Influence-Guided Symbolic Regression (IGSR), a novel framework that uses granular influence scores to guide LLMs in efficiently searching for and discovering complex mathematical…

BIRDNet is a novel, sparse, and interpretable deep neural network that encodes Boolean implication knowledge mined directly from tabular data, achieving performance comparable to dense models while dr…

The paper introduces Chunk-Level Guided Generation, a training-free method that uses an off-the-shelf large language model (LLM) as a process scorer to guide small model generation, achieving performa…

The paper introduces retraining-free frameworks (Meow2X and TRNE) that mechanistically localize and suppress toxicity within language models by analyzing activation differences, achieving safety impro…

This paper evaluates the causal reasoning abilities of large language models and finds that they rely heavily on lexical pattern matching rather than structural reasoning.

The paper proposes a local perturbation theory showing that cross-domain interference in multi-domain RL occurs via a low-dimensional shared conflict subspace, which can be selectively mitigated by sh…

The paper introduces ProtStructQA, an executable benchmark that tests protein structural reasoning by requiring language models to generate measurable 3D coordinates, revealing a capability-dependent…

MolLingo is a multi-agent system that significantly improves automated molecular design by integrating domain-specific chemical reasoning and structural context into LLMs, outperforming state-of-the-a…

The paper demonstrates that increasing the toxicity of prompts significantly degrades the factual reliability of LLMs, a degradation linked to the selective amplification of perturbation-sensitive nod…

The paper introduces Query2Effect, a large-scale benchmark, and a two-step framework to predict causal effect sizes from natural language queries, showing that structured representation significantly…

The paper introduces Contrastive Reflection (CORE), a novel non-parametric method that rapidly improves language model reasoning by distilling contrasts between successful and unsuccessful problem att…

The paper compares verbalized feature attributions and self-generated rationales for explaining model behavior, finding that the format and granularity of the explanation significantly affect its abil…

The paper systematically evaluates concept-based explainability in MLLMs, finding that forcing models to generate formal explanations degrades predictive accuracy, suggesting that explaining is genuin…

The paper proposes sampling directly from approximations of an LLM posterior, conditioned on high-scoring regions, to generate more coherent and useful text compared to existing post-hoc hallucination…

The paper introduces Ryze, an automated system that synthesizes evidence-enriched Question-Answering (QA) pairs from raw biomedical papers, resulting in a specialized VLM (BioVLM-8B) that significantl…

The paper identifies a failure mode called spatial lexical bias in MLLMs, where adding a spatial word to options biases the model's choice, and demonstrates that this failure originates primarily from…