Related papers: On Mechanistic Circuits for Extractive Question-An…

Recent advancements in artificial intelligence have sparked interest in the parallels between large language models (LLMs) and human neural processing, particularly in language comprehension. While prior research has established…

Given a sequence of tokens generated by a language model, we may want to identify the preceding tokens that influence the model to generate this sequence. Performing such token attribution is expensive; a common approach is to ablate…

Large language models (LLMs) have demonstrated remarkable performance across various real-world tasks. However, they often struggle to fully comprehend and effectively utilize their input contexts, resulting in responses that are unfaithful…

LLMs can help humans working with long documents, but are known to hallucinate. Attribution can increase trust in LLM responses: The LLM provides evidence that supports its response, which enhances verifiability. Existing approaches to…

Fine-tuning large pre-trained language models on downstream tasks is apt to suffer from overfitting when limited training data is available. While dropout proves to be an effective antidote by randomly dropping a proportion of units,…

Rule extraction is a central problem in interpretable machine learning because it seeks to convert opaque predictive behavior into human-readable symbolic structure. This paper presents Chat Incremental Pattern Constructor (ChatIPC), a…

Access to external knowledge is essential for many natural language processing tasks, such as question answering and dialogue. Existing methods often rely on a parametric model that stores knowledge in its parameters, or use a…

Keyphrase extraction from a given document is the task of automatically extracting salient phrases that best describe the document. This paper proposes a novel unsupervised graph-based ranking method to extract high-quality phrases from a…

Large language models (LLMs) provide capabilities far beyond sentence completion, including question answering, summarization, and natural-language inference. While many of these capabilities have potential application to cognitive systems,…

Generating high-quality answers consistently by providing contextual information embedded in the prompt passed to the Large Language Model (LLM) is dependent on the quality of information retrieval. As the corpus of contextual information…

Tacit knowledge plays a central role in human expertise, yet it remains difficult to capture, formalize, and reuse in machine-interpretable form. This challenge is especially relevant in procedural domains, where successful execution…

Large Language Models (LLMs) have shown remarkable performance in multi-turn dialogue. However, in multi-turn dialogue, models still struggle to stay aligned with what has been established earlier, follow dependencies across many turns, and…

Large Language Models (LLMs) often struggle to maintain their original performance when faced with semantically coherent but task-irrelevant contextual information. Although prior studies have explored this issue using fixed-template or…

Extractive summarization is a crucial task in natural language processing that aims to condense long documents into shorter versions by directly extracting sentences. The recent introduction of large language models has attracted…

Machine Reading Comprehension (MRC) poses a significant challenge in the field of Natural Language Processing (NLP). While mainstream MRC methods predominantly leverage extractive strategies using encoder-only models such as BERT,…

Driving in safety-critical scenarios requires quick, context-aware decision-making grounded in both situational understanding and experiential reasoning. Large Language Models (LLMs), with their powerful general-purpose reasoning…

Large language models (LLMs) increasingly rely on chain-of-thought (CoT) reasoning to solve complex tasks. Yet ensuring that the reasoning trace both contributes to and faithfully reflects the processes underlying the model's final answer,…

Neural models have demonstrated remarkable performance across diverse ranking tasks. However, the processes and internal mechanisms along which they determine relevance are still largely unknown. Existing approaches for analyzing neural…

Large language models (LLMs) present a promising yet challenging frontier for automated source citation in scientific communication. Previous approaches to citation generation have been limited by citation ambiguity and LLM…

Chain-of-thought (CoT) rationale enables language models to use additional task-related text for problem-solving, benefiting not only from detailed reasoning steps but also from the expanded computational space of longer inputs. Prior work…