Related papers: Discovering Knowledge Deficiencies of Language Mod…

Achieving reliable communication has long been a fundamental challenge in networked systems. Semantic Error Correction (SEC) leverages the semantic understanding capabilities of language models (LMs) to perform application-layer error…

Reinforcement learning (RL) has been pivotal in enhancing the reasoning capabilities of large language models (LLMs), but it often suffers from limited exploration and entropy collapse, where models exploit a narrow set of solutions,…

Large Language Models (LLMs) have exhibited remarkable capabilities across diverse domains, prompting investigations into their potential as generic reasoning engines. While recent studies have explored inference-time computation to enhance…

Continual fine-tuning of large language models (LLMs) suffers from catastrophic forgetting. Rehearsal-based methods mitigate this problem by retaining a small set of old data. Nevertheless, they still suffer inevitable performance loss.…

Large language models (LLMs) acquire substantial world knowledge during pre-training, which is further shaped by post-training techniques such as supervised fine-tuning (SFT). However, the impact of SFT on a model's knowledge remains…

Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text, typically in the form of (subject, relation, object) triples. Despite the potential of large language models (LLMs) like ChatGPT as a general…

This study delves into the capabilities and limitations of Large Language Models (LLMs) in the challenging domain of conditional question-answering. Utilizing the Conditional Question Answering (CQA) dataset and focusing on generative…

Current approaches to data discovery match keywords between metadata and queries. This matching requires researchers to know the exact wording that other researchers previously used, creating a challenging process that could lead to missing…

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Feature discovery from complex unstructured data is fundamentally a reasoning problem: it requires identifying abstractions that are predictive of a target outcome while avoiding leakage, proxies, and post-outcome signals. With the…

Pretrained Language Models (PLMs) store extensive knowledge within their weights, enabling them to recall vast amount of information. However, relying on this parametric knowledge brings some limitations such as outdated information or gaps…

Large Language Models (LLMs) often produce fluent yet factually incorrect statements-a phenomenon known as hallucination-posing serious risks in high-stakes domains. We present Layer-wise Semantic Dynamics (LSD), a geometric framework for…

The zero-shot capability of Large Language Models (LLMs) has enabled highly flexible, reference-free metrics for various tasks, making LLM evaluators common tools in NLP. However, the robustness of these LLM evaluators remains relatively…

Harmful fine-tuning attacks pose a major threat to the security of large language models (LLMs), allowing adversaries to compromise safety guardrails with minimal harmful data. While existing defenses attempt to reinforce LLM alignment,…

Reading comprehension is a key for individual success, yet the assessment of question difficulty remains challenging due to the extensive human annotation and large-scale testing required by traditional methods such as linguistic analysis…

Event extraction has gained extensive research attention due to its broad range of applications. However, the current mainstream evaluation method for event extraction relies on token-level exact match, which misjudges numerous…

Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges. Caching inference responses, allowing them to be retrieved…

Cascaded Automatic Speech Recognition -- Large Language Model (ASR-LLM) pipelines remain popular for industrial Spoken Dialogue Systems (SDS), primarily because their decoupled design ensures perceptual verifiability. However, cascaded…

Industrial machine fault diagnosis is a critical component of operational efficiency and safety in manufacturing environments. Traditional methods rely heavily on expert knowledge and specific machine learning models, which can be limited…

The evaluation and improvement of medical large language models (LLMs) are critical for their real-world deployment, particularly in ensuring accuracy, safety, and ethical alignment. Existing frameworks inadequately dissect domain-specific…