Related papers: You Only Forward Once: Prediction and Rationalizat…

Backpropagation remains the dominant algorithm for training deep neural networks, but it incurs substantial memory overhead and relies on global error propagation, which is often regarded as biologically implausible. The Forward-Forward…

Interpretability or explainability is an emerging research field in NLP. From a user-centric point of view, the goal is to build models that provide proper justification for their decisions, similar to those of humans, by requiring the…

Rationalization is to employ a generator and a predictor to construct a self-explaining NLP model in which the generator selects a subset of human-intelligible pieces of the input text to the following predictor. However, rationalization…

Relation extraction (RE) aims to extract potential relations according to the context of two entities, thus, deriving rational contexts from sentences plays an important role. Previous works either focus on how to leverage the entity…

Language models often struggle with idiomatic, figurative, or context-sensitive inputs, not because they produce flawed outputs, but because they misinterpret the input from the outset. We propose an input-only method for anticipating such…

Supervised fine-tuning (SFT) has emerged as one of the most effective ways to improve the performance of large language models (LLMs) in downstream tasks. However, SFT can have difficulty generalizing when the underlying data distribution…

In a multi-stage recommendation system, reranking plays a crucial role in modeling intra-list correlations among items. A key challenge lies in exploring optimal sequences within the combinatorial space of permutations. Recent research…

Balancing exploration and exploitation remains a central challenge in reinforcement learning with verifiable rewards (RLVR) for large language models (LLMs). Current RLVR methods often overemphasize exploitation, leading to entropy…

Autoregressive language models trained with next-token prediction generate text by sampling one discrete token at a time. Although very scalable, this objective forces the model to commit at every step, preventing it from exploring or…

Neural Forecasters (NFs) have become a cornerstone of Long-term Time Series Forecasting (LTSF). However, recent progress has been hampered by an overemphasis on architectural complexity at the expense of fundamental forecasting structures.…

Maximum entropy reinforcement learning (MaxEnt RL) has become a standard framework for sequential decision making, yet its standard Gaussian policy parameterization is inherently unimodal, limiting its ability to model complex multimodal…

Visual reasoning, often interleaved with intermediate visual states, has emerged as a promising direction in the field. A straightforward approach is to directly generate images via unified models during reasoning, but this is…

Large language models (LLMs) are typically pretrained with next-word prediction (NWP), which yields strong surface fluency but places limited pressure on models to form explicit reasoning before emitting tokens. We study whether shifting…

Long-sequence transformers are designed to improve the representation of longer texts by language models and their performance on downstream document-level tasks. However, not much is understood about the quality of token-level predictions…

Self-Consistency samples diverse reasoning chains with answers and chooses the final answer by majority voting. It is based on forward reasoning and cannot further improve performance by sampling more reasoning chains when saturated. To…

Reasoning language models can solve increasingly complex tasks, but struggle to produce the calibrated confidence estimates necessary for reliable deployment. Existing calibration methods usually depend on labels or repeated sampling at…

We develop a rigorous walk-forward validation framework for algorithmic trading designed to mitigate overfitting and lookahead bias. Our methodology combines interpretable hypothesis-driven signal generation with reinforcement learning and…

Explaining the predictions of AI models is paramount in safety-critical applications, such as in legal or medical domains. One form of explanation for a prediction is an extractive rationale, i.e., a subset of features of an instance that…

Uncertainty estimation for reasoning language models remains difficult to deploy in practice: sampling-based methods are computationally expensive, while common single-pass proxies such as verbalized confidence or trace length are often…

We introduce Forecasting Argumentation Frameworks (FAFs), a novel argumentation-based methodology for forecasting informed by recent judgmental forecasting research. FAFs comprise update frameworks which empower (human or artificial) agents…