Related papers: BoundRL: Efficient Structured Text Segmentation th…
Large language models (LLMs) have achieved impressive performance on knowledge-intensive tasks, yet they often struggle with multi-step reasoning due to the unstructured nature of retrieved context. While retrieval-augmented generation…
Reinforcement learning with verifiable rewards (RLVR) has significantly improved reasoning in large language models (LLMs), yet the token-level mechanisms underlying these improvements remain unclear. We present a systematic empirical study…
Large Language Models (LLMs) have shown remarkable prowess in text generation, yet producing long-form, factual documents grounded in extensive external knowledge bases remains a significant challenge. Existing "top-down" methods, which…
Effective code generation with language models hinges on two critical factors: accurately understanding the intent of the prompt and generating code that applies algorithmic reasoning to produce correct solutions capable of passing diverse…
An ideal detection system for machine generated content is supposed to work well on any generator as many more advanced LLMs come into existence day by day. Existing systems often struggle with accurately identifying AI-generated content…
The applications of LLM Agents are becoming increasingly complex and diverse, leading to a high demand for structured outputs that can be parsed into code, structured function calls, and embodied agent commands. These developments bring…
Deep Reinforcement Learning (RL) is remarkably effective in addressing sequential resource allocation problems in domains such as healthcare, public policy, and resource management. However, deep RL policies often lack transparency and…
While Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for boosting large language models (LLMs) in knowledge-intensive tasks, it often overlooks the crucial aspect of text chunking within its workflow. This paper…
The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…
In arbitrary shape text detection, locating accurate text boundaries is challenging and non-trivial. Existing methods often suffer from indirect text boundary modeling or complex post-processing. In this paper, we systematically present a…
Reinforcement learning (RL) has become a standard paradigm for refining large language models (LLMs) beyond pre-training and instruction tuning. A prominent line of work is RL with verifiable rewards (RLVR), which leverages automatically…
Learning word representations has recently seen much success in computational linguistics. However, assuming sequences of word tokens as input to linguistic analysis is often unjustified. For many languages word segmentation is a…
Query-focused summarization (QFS) aims to provide a summary of a document that satisfies information need of a given query and is useful in various IR applications, such as abstractive snippet generation. Current QFS approaches typically…
Large Language Models (LLMs) encode meanings of words in the form of distributed semantics. Distributed semantics capture common statistical patterns among language tokens (words, phrases, and sentences) from large amounts of data. LLMs…
Machine learning models are widely used for real-world applications, such as document analysis and vision. Constrained machine learning problems are problems where learned models have to both be accurate and respect constraints. For…
Large Language Models (LLMs) excel at generating fluent text but struggle to enforce external constraints because they generate tokens sequentially without explicit control mechanisms. GenCP addresses this limitation by combining LLM…
Reasoning over long contexts is essential for large language models. While reinforcement learning (RL) enhances short-context reasoning by inducing "Aha" moments in chain-of-thought, the advanced thinking patterns required for long-context…
To obtain high-quality sentence embeddings from pretrained language models (PLMs), they must either be augmented with additional pretraining objectives or finetuned on a large set of labeled text pairs. While the latter approach typically…
This thesis addresses automatic lexical error recovery and tokenization of corrupt text input. We propose a technique that can automatically correct misspellings, segmentation errors and real-word errors in a unified framework that uses…
Large language models (LLMs) have demonstrated remarkable capabilities across various domains, yet their application to relational deep learning (RDL) remains underexplored. Existing approaches adapt LLMs by traversing relational links…