18 accepted papers
Post-training endows pretrained LLMs with a variety of desirable skills, such as instruction-following, reasoning, and others. However, these post-trained LLMs only encode knowledge up to a cut-off date, necessitating continual adaptation. Unfortunately, existing solutions cannot effectively learn n…
LLMs cannot reliably recognize their parametric knowledge boundaries and often hallucinate answers to outside-of-boundary questions. In this paper, we introduce MASH (Modeling Abstention via Selective Help-seeking), a training framework that readily extracts abstentions from LLMs. Our key idea is th…
Reasoning LLMs are trained to verbalize their thinking process, yielding strong gains on complex tasks. This transparency also opens a promising direction: multiple reasoners can directly collaborate on each other's thinking on a shared trajectory, yielding better inference efficiency and exploratio…
Recently, open community-driven platforms like Chatbot Arena that collect user preference data from site visitors have gained reputation as trustworthy publicly available benchmarks for LLM performance. While gold standard, it is often tricky to implement the required guardrails to collect high-qual…
Recent research has attempted to associate preference optimization (PO) performance with the underlying preference datasets. In this work, our observation is that the differences between the preferred response y + and dispreferred response y - influence what LLMs can learn, which may not match the d
Large language models (LLMs) encode vast amounts of pre-trained knowledge in their parameters, but updating them as real-world information evolves remains a challenge. Existing methodologies and benchmarks primarily target entity substitutions, failing to capture the full breadth of complex real-wor…
Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is constructing a smaller key-value (KV) cache, relieving LLMs from computing attention over a long sequence of to…
LLM judges have gained popularity as an inexpensive and performant substitute for human evaluation. However, we observe that the meta-evaluation setting in which the reliability of these LLM evaluators is established is substantially different from their use in model development. To address this, we
Summarizing book-length documents ($>$100K tokens) that exceed the context window size of large language models (LLMs) requires first breaking the input document into smaller chunks and then prompting an LLM to merge, update, and compress chunk-level summaries. Despite the complexity and importance…
As research in large language models (LLMs) continues to accelerate, LLM-based evaluation has emerged as a scalable and cost-effective alternative to human evaluations for comparing the ever increasing list of models. This paper investigates the efficacy of these “LLM evaluators”, particularly in us…
Literature search questions, such as “where can I find research on the evaluation of consistency in generated summaries?” pose significant challenges for modern search engines and retrieval systems. These questions often require a deep understanding of research concepts and the ability to reason ove…
Synthetic long-context LLM benchmarks (e.g., “needle-in-the-haystack”) test only surface-level retrieval capabilities; but how well can long-context LLMs retrieve, synthesize, and reason over information across book-length inputs? We address this question by creating NoCha, a dataset of 1,001 minima…
The propensity of abstractive summarization models to make factual errors has been studied extensively, including design of metrics to detect factual errors and annotation of errors in current systems’ outputs. However, the ever-evolving nature of summarization systems, metrics, and annotated benchm…
Textual entailment models are increasingly applied in settings like fact-checking, presupposition verification in question answering, or summary evaluation. However, these represent a significant domain shift from existing entailment datasets, and models underperform as a result. We propose WiCE, a…
Summarization systems make numerous “decisions” about summary properties during inference, e.g. degree of copying, specificity and length of outputs, etc. However, these are implicitly encoded within model parameters and specific styles cannot be enforced. To address this, we introduce HydraSum, a n…
Progress in summarizing long texts is inhibited by the lack of appropriate evaluation frameworks. A long summary that appropriately covers the facets of that text must also present a coherent narrative, but current automatic and human evaluation methods fail to identify gaps in coherence. In this wo…
Pre-trained language models (e.g. BART) have shown impressive results when fine-tuned on large summarization datasets. However, little is understood about this fine-tuning process, including what knowledge is retained from pre-training time or how content selection and generation strategies are lear…
Recent pre-trained abstractive summarization systems have started to achieve credible performance, but a major barrier to their use in practice is their propensity to output summaries that are not faithful to the input and that contain factual errors. While a number of annotated datasets and statist…