Papers

Introduction If you have ever asked ChatGPT or GitHub Copilot to write a Python script or a JavaScript function, you know the results can be magically accurate. These models have been trained on billions of lines of code from popular languages, making them incredibly proficient at standard programming tasks. But what happens when you step off the beaten path? When you ask an LLM to generate code for low-resource languages—domain-specific languages (DSLs) like Microsoft Power Query M, OfficeScript, or complex Excel formulas—the performance drops significantly. These languages don’t have the massive repositories of open-source code required to train a model effectively. ...

Beyond Wikipedia: Benchmarking Long-Form RAG with LFRQA and RAG-QA Arena Retrieval-Augmented Generation (RAG) has become the de facto architecture for building reliable AI systems. By connecting Large Language Models (LLMs) to external data sources, we give them a “memory” that is up-to-date and verifiable. However, a significant gap exists in how we evaluate these systems. Most current benchmarks rely on Wikipedia data and expect short, punchy answers (like “Paris” or “1984”). But in the real world, we use RAG to generate comprehensive reports, summarize financial trends, or explain complex biological mechanisms. When an LLM generates a nuanced, three-paragraph explanation, comparing it to a three-word ground truth using standard “exact match” metrics is like grading a history essay with a math answer key. ...

The release of Large Language Models (LLMs) like ChatGPT and LLaMA has fundamentally changed how we generate text. From writing emails to coding, the utility is undeniable. However, this power comes with a shadow: academic dishonesty, disinformation campaigns, and sophisticated phishing. To counter this, a new industry of “AI Detectors” has emerged—tools designed to distinguish between human and machine-written content. But how robust are these guardians? In this post, we dive deep into a paper titled “RAFT: Realistic Attacks to Fool Text Detectors,” which proposes a novel framework for “red-teaming” (attacking) these detectors. Unlike previous methods that often produce garbled or grammatically incorrect text, RAFT generates attacks that are essentially invisible to the human eye but confusing enough to break the best detectors available. ...

In the rapidly evolving world of Large Language Models (LLMs), engineers and researchers are constantly battling a frustrating trade-off: Speed versus Faithfulness. Imagine you are building a chatbot for a hotel. A user asks, “Do you have vegan breakfast options?” Option A: The bot answers instantly (0.5 seconds), but it hallucinates and says “Yes,” when you actually don’t. This is fast but dangerous. Option B: The bot pauses, retrieves the latest menu from a database, reads it, and answers correctly. This takes 3-5 seconds. This is accurate but feels sluggish to the user. Option A represents Retrieval Free Generation (RFG), where the model relies on its internal memory. Option B represents Retrieval Augmented Generation (RAG), the current gold standard for accuracy. ...

The world of Natural Language Processing (NLP) has been dominated by classical giants—Recurrent Neural Networks (RNNs), LSTMs, and more recently, Transformers. These models rely on massive computational resources and millions (sometimes billions) of parameters to understand human language. But a new paradigm is emerging: Quantum Computing. For years, the intersection of Quantum Computing and NLP—often called QNLP—was largely theoretical. However, as we approach the era of “quantum advantage,” researchers are asking a pivotal question: Can quantum models perform sequential tasks like text classification, and can they do it efficiently? ...

When we look at a photograph, we assume we are seeing objective reality. If you show a picture of a park to a person in New York and a person in Munich, surely they are seeing the same grass, the same benches, and the same sky. But are they? Cognitive science and psychology suggest that visual perception is deeply tied to culture. A Western viewer might focus intently on the foreground objects—the specific people or the specific make of a car. An East Asian viewer might place significantly more weight on the context, the background, and the relationships between objects. ...

The capabilities of Large Language Models (LLMs) have exploded in recent years, but they still have a critical limitation: they are confined to their training data. To solve real-world problems—like checking the weather, querying a database, or performing complex math—LLMs need to use external tools. Training a model to use tools (APIs) usually requires massive amounts of data containing instructions and the corresponding API calls. Because creating this data by hand is expensive, researchers rely heavily on synthetic data generated by other LLMs (like GPT-4). ...

Imagine you are trying to find your keys in a pitch-black room. You reach out and feel a smooth, cold surface. If you assume you are touching the kitchen counter, you might start feeling around for the fruit bowl. But if you were actually touching a glass table in the living room, every subsequent move you take is based on a false premise. You aren’t just lost; you are actively moving further away from your goal. ...

Introduction We often treat Large Language Models (LLMs) like omniscient reasoning engines. We feed them complex scenarios, legal documents, or medical summaries and ask them to derive conclusions. But how good are these models really when the answers aren’t black and white? In the real world, certainty is a luxury. A doctor doesn’t say “This symptom always means X.” They say, “Given this symptom, the diagnosis is highly likely to be X, unless Y is also present.” This is probabilistic reasoning—the ability to handle uncertainty, weigh evidence, and update beliefs. ...

Large Language Models (LLMs) like LLaMA-2 and Falcon have revolutionized AI, but they come with a hefty price tag: computational cost. Running these massive models requires significant GPU memory and processing power. To make these models accessible on local hardware or cheaper cloud instances, researchers have been racing to compress them. The most common technique is quantization—reducing the precision of the numbers used to represent the model. Instead of using 16-bit floating-point numbers (FP16), we try to squeeze them into 8 bits or even 4 bits. ...

When we read a news article or follow a complex narrative, we don’t process sentences in isolation. We instinctively look for connections. We ask ourselves: Why is the author saying this? What question does this sentence answer regarding the previous one? This cognitive process is the foundation of a linguistic framework known as Question Under Discussion (QUD). It treats discourse as a hierarchy of questions and answers. While humans do this naturally, teaching machines to parse these structures is notoriously difficult. Existing models often struggle to generate questions that make sense within the context or fail to link sentences correctly. ...

Imagine you are building an AI tutor designed to help students study for history exams. You feed the AI a textbook chapter about the Mongol Empire and ask it to generate quiz questions. The AI outputs: “Who was the name of Ögedei’s wife?” Grammatically, it’s a bit clunky. But technically, if you look at the source text, the words match. Traditional evaluation metrics might give this a decent score. However, a human student would find it confusing. ...

The rise of Large Language Models (LLMs) like GPT-4 and LLaMA has been nothing short of meteoric. We have seen them pass bar exams, write code, and compose poetry. However, there is a distinct difference between generating fluent text and performing rigorous logical reasoning. While an LLM can explain the history of chess, can it actually play chess at a high level? Can it solve a cryptic crossword or deduce the location of a mine in Minesweeper? ...

Introduction: The Crisis and the Gap Suicide remains one of the most critical public health challenges globally. Every loss of life is a tragedy that ripples through families and communities. As mental health awareness grows, more individuals are turning to online counseling services for help. These platforms offer immediate, confidential support, breaking down barriers of time and space. However, as the volume of users increases, human counselors can become overwhelmed. This is where Artificial Intelligence (AI) steps in. For years, researchers have been developing automated systems to detect suicidal ideation in text. Yet, there is a significant flaw in the current landscape: most existing systems treat suicide detection as a simple binary problem—Suicidal or Non-Suicidal. ...

Imagine the high-pressure job of a simultaneous interpreter at the United Nations. They listen to a speech in one language and must translate it into another in real-time. If they wait too long to hear the full sentence, they fall behind (high latency). If they translate too soon, they might guess wrong and make a mistake (low quality). They must constantly decide: Do I speak now, or do I listen for one more word? ...

Introduction The race for larger, more capable Large Language Models (LLMs) like Llama-3 and Mistral has led to incredible breakthroughs in artificial intelligence. However, this progress comes with a massive cost. As these models scale to billions of parameters, they become increasingly difficult to deploy in resource-limited environments. Running a 70-billion parameter model on a consumer-grade GPU—or worse, a mobile device—is often a non-starter due to memory and energy constraints. ...

Have you ever asked an AI to write an essay on a controversial topic? Often, the result looks impressive at first glance. The grammar is perfect, the vocabulary is sophisticated, and the structure seems sound. But if you look closer, cracks begin to appear. The AI might make a bold claim in the first sentence, only to provide evidence that contradicts it three sentences later. Or, it might list facts that are technically true but irrelevant to the argument at hand. ...

In the history of Artificial Intelligence, we mark progress by the fallen champions of humanity. We remember when Deep Blue defeated Garry Kasparov at chess. We remember when AlphaGo stunned Lee Sedol. These were pivotal moments where machines proved they could out-calculate the best human minds in closed systems of logic and strategy. But art is not a closed system. For years, we have comforted ourselves with the idea that while machines crunch numbers, humans create meaning. However, the rise of Large Language Models (LLMs) like GPT-4 has brought an uneasy question to the surface: Are we losing the creative frontier, too? We know AI can write competent emails and passable high school essays. We know it can outperform the average human writer. ...

Introduction In the rapidly evolving landscape of Natural Language Processing (NLP), Large Language Models (LLMs) like GPT-4 and Llama-3 have become the de facto standard for generating text, writing code, and answering questions. Their ability to understand context is unparalleled. However, a significant challenge remains: how do we use these generative giants to effectively find information within massive datasets without breaking the bank? Traditionally, utilizing LLMs for Information Retrieval (IR) has fallen into two distinct but imperfect camps. First, there are prompt-based re-ranking methods. In this scenario, you retrieve a small set of documents using a simple keyword search and then ask the LLM, “Is this document relevant to the user’s query?” While this yields high accuracy, it is computationally excruciating. Imagine running a massive model like GPT-4 hundreds of times for every single search query; it is too slow and costly for real-time applications. ...

The explosion of Large Language Models (LLMs) has created a peculiar bottleneck in artificial intelligence. We have models that can write poetry, code, and legal briefs, but we are running out of reliable ways to grade them. Historically, humans were the judges. But humans are slow, expensive, and often inconsistent. To solve this, the industry shifted toward the “LLM-as-a-Judge” paradigm, where powerful proprietary models like GPT-4 evaluate the outputs of smaller models. It works well, but it introduces new problems: high costs, lack of transparency (closed source), and data privacy concerns. ...