Related papers: Decomposed Prompting Does Not Fix Knowledge Gaps, …
An important open question in the use of large language models for knowledge-intensive tasks is how to effectively integrate knowledge from three sources: the model's parametric memory, external structured knowledge, and external…
The remarkable success of pretrained language models has motivated the study of what kinds of knowledge these models learn during pretraining. Reformulating tasks as fill-in-the-blanks problems (e.g., cloze tests) is a natural approach for…
Language models (LMs) often struggle to pay enough attention to the input context, and generate texts that are unfaithful or contain hallucinations. To mitigate this issue, we present context-aware decoding (CAD), which follows a…
Large pre-trained language models have demonstrated their proficiency in storing factual knowledge within their parameters and achieving remarkable results when fine-tuned for downstream natural language processing tasks. Nonetheless, their…
Large language models often generate confident but incorrect answers rather than abstaining when uncertain. This problem is particularly acute for small language models (SLMs), where computational constraints and autonomous operation…
A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability. Three situations where this is particularly apparent are correctness, hallucinations when given unanswerable questions, and…
Large language models exhibit sycophancy, the tendency to shift their stated positions toward perceived user preferences or authority cues regardless of evidence. Standard alignment methods fail to correct this because scalar reward models…
Mitigating hallucinations in Large Language Models (LLMs) is critical for their reliable deployment. Existing methods typically fine-tune LLMs to abstain from answering questions beyond their knowledge scope. However, these methods often…
Grounding responses in external knowledge represents an effective strategy for mitigating hallucinations in Large Language Models (LLMs). However, current LLMs struggle to seamlessly integrate knowledge while simultaneously maintaining…
Can Large Language Models (LLMs) be trained to avoid hallucinating factual statements, and can Retrieval-Augmented Generation (RAG) be triggered only when necessary to reduce retrieval and computation costs? In this work, we address both…
Understanding why a large language model (LLM) is uncertain about the response is important for their reliable deployment. Current approaches, which either provide a single uncertainty score or rely on the classical aleatoric-epistemic…
Explicit decomposition modeling, which involves breaking down complex tasks into more straightforward and often more interpretable sub-tasks, has long been a central theme in developing robust and interpretable NLU systems. However, despite…
Failures in large language models (LLMs) are often analyzed from a behavioral perspective, where incorrect outputs in factual question answering are commonly associated with missing knowledge. In this work, focusing on entity-based factual…
Large Language Models (LLMs) often exhibit \textit{hallucinations}, generating factually incorrect or semantically irrelevant content in response to prompts. Chain-of-Thought (CoT) prompting can mitigate hallucinations by encouraging…
Fact-checking pipelines increasingly adopt the Decompose-Then-Verify paradigm, where texts are broken down into smaller claims for individual verification and subsequently combined for a veracity decision. While decomposition is…
Large language models (LLMs) often solve a task when all instructions are given in a single prompt, but fail when the same information is revealed gradually across turns. When a clean FULL prompt and a RAW-SHARDED conversation contain the…
Causal language models acquire vast amount of knowledge from general text corpus during pretraining, but the efficiency of knowledge learning is known to be unsatisfactory, especially when learning from knowledge-dense and small-sized…
Large Language Models (LLMs) are widely used by students, yet their tendency to provide fast and complete answers may discourage reflection and foster overconfidence. We examined how alternative LLM interaction designs support deeper…
The most common training pipeline for large language models includes pretraining, finetuning and aligning phases, with their respective resulting models, such as the pretrained model and the finetuned model. Finetuned and aligned models…
Knowledge augmentation has significantly enhanced the performance of Large Language Models (LLMs) in knowledge-intensive tasks. However, existing methods typically operate on the simplistic premise that model performance equates with…