Large pre-trained language models have been shown to store factual knowledge in their parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, their ability to access and precisely manipulate knowledge is still limited, and hence on knowledge-intensive tasks, their performance lags behind task-specific architectures. Additionally, providing provenance for their decisions and updating their world knowledge remain open research problems. Pre-trained models with a differentiable access mechanism to explicit non-parametric memory can overcome this issue, but have so far been only investigated for extractive downstream tasks. We explore a general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation.

In this work, we introduce a novel approach called Scaling to Emphasize Attention for Long-context retrieval (SEAL), which enhances the retrieval performance of large language models (LLMs) over extended contexts. Previous studies have shown that each attention head in LLMs has a unique functionality and collectively contributes to the overall behavior of the model. Similarly, we observe that specific heads are closely tied to long-context retrieval, showing positive or negative correlation with retrieval scores. Built on this insight, we propose a learning-based mechanism using zero-shot generated data to emphasize these heads, improving the model's performance in long-context retrieval tasks. By applying SEAL, we can achieve significant improvements in in-domain retrieval performance, including document QA tasks from LongBench, and considerable improvements in outof-domain cases. Additionally, when combined with existing training-free context extension techniques, SEAL extends the context limits of LLMs while maintaining highly reliable outputs, opening new avenues for research in this field. Large Language Models (LLMs) (Brown et al. (2020), Radford et al. (2019), Touvron et al. (2023)) are capable of rapidly generating high-quality answers to a wide range of questions by leveraging the diverse knowledge embedded in their vast number of parameters. However, in-depth analyses have revealed a common issue known as hallucination (Shuster et al. (2021), Lin et al. (2021), Ji et al. (2023)), where the models confidently produce inaccurate answers. Figure 1: Overview of the proposed SEAL and corresponding retrieval score improvements for LongChat-7B-v1.5-32K These approaches have significantly improved the reliability of LLMs by enabling them to reference existing information during generation. However, this trend has also highlighted a key limitation of LLMs: the constraint of their context window length.

Large language models (LLMs) have demonstrated immense capabilities in understanding textual data and are increasingly being adopted to help researchers accelerate scientific discovery through knowledge extraction (information retrieval), knowledge distillation (summarizing key findings and methodologies into concise forms), and knowledge synthesis (aggregating information from multiple scientific sources to address complex queries, generate hypothesis and formulate experimental plans). However, scientific data often exists in both visual and textual modalities. Vision language models (VLMs) address this by incorporating a pretrained vision backbone for processing images and a cross-modal projector that adapts image tokens into the LLM dimensional space, thereby providing richer multimodal comprehension. Nevertheless, off-the-shelf VLMs show limited capabilities in handling domain-specific data and are prone to hallucinations. We developed intelligent assistants finetuned from LLaVA models to enhance multimodal understanding in low-dose radiation therapy (LDRT)-a benign approach used in the treatment of cancer-related illnesses. Using multilingual data from 42,673 articles, we devise complex reasoning and detailed description tasks for visual question answering (VQA) benchmarks. Our assistants, trained on 50,882 image-text pairs, demonstrate superior performance over base models as evaluated using LLM-as-a-judge approach, particularly in reducing hallucination and improving domain-specific comprehension.

Recently, numerous benchmarks have been developed to evaluate the logical reasoning abilities of large language models (LLMs). However, assessing the equally important creative capabilities of LLMs is challenging due to the subjective, diverse, and data-scarce nature of creativity, especially in multimodal scenarios. In this paper, we consider the comprehensive pipeline for evaluating the creativity of multimodal LLMs, with a focus on suitable evaluation platforms and methodologies. First, we find the Oogiri game, a creativity-driven task requiring humor, associative thinking, and the ability to produce unexpected responses to text, images, or both. This game aligns well with the input-output structure of modern multimodal LLMs and benefits from a rich repository of high-quality, human-annotated creative responses, making it an ideal platform for studying LLM creativity. Next, beyond using the Oogiri game for standard evaluations like ranking and selection, we propose LoTbench, an interactive, causality-aware evaluation framework, to further address some intrinsic risks in standard evaluations, such as information leakage and limited interpretability. The proposed LoTbench not only quantifies LLM creativity more effectively but also visualizes the underlying creative thought processes. Our results show that while most LLMs exhibit constrained creativity, the performance gap between LLMs and humans is not insurmountable. Furthermore, we observe a strong correlation between results from the multimodal cognition benchmark MMMU and LoTbench, but only a weak connection with traditional creativity metrics. This suggests that LoTbench better aligns with human cognitive theories, highlighting cognition as a critical foundation in the early stages of creativity and enabling the bridging of diverse concepts. https://lotbench.github.io

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences between preferred and rejected responses enhance learning performance. Current methods for identifying and obtaining such high-quality samples demand additional resources or external models. We discover that reference model probability space naturally detects high-quality training samples. Using this insight, we present a sampling strategy that achieves consistent improvements (+0.1 to +0.4) on MT-Bench while using less than half (30-50%) of the training data. We observe substantial improvements (+0.4 to +0.98) for technical tasks (coding, math, and reasoning) across multiple models and hyperparameter settings.

Artificial Intelligence has become a double edged sword in modern society being both a boon and a bane. While it empowers individuals it also enables malicious actors to perpetrate scams such as fraudulent phone calls and user impersonations. This growing threat necessitates a robust system to protect individuals In this paper we introduce a novel real time fraud detection mechanism using Retrieval Augmented Generation technology to address this challenge on two fronts. First our system incorporates a continuously updating policy checking feature that transcribes phone calls in real time and uses RAG based models to verify that the caller is not soliciting private information thus ensuring transparency and the authenticity of the conversation. Second we implement a real time user impersonation check with a two step verification process to confirm the callers identity ensuring accountability. A key innovation of our system is the ability to update policies without retraining the entire model enhancing its adaptability. We validated our RAG based approach using synthetic call recordings achieving an accuracy of 97.98 percent and an F1score of 97.44 percent with 100 calls outperforming state of the art methods. This robust and flexible fraud detection system is well suited for real world deployment.

The rapid increase in the parameter counts of Large Language Models (LLMs), reaching billions or even trillions, presents significant challenges for their practical deployment, particularly in resource-constrained environments. To ease this issue, we propose PIP (Perturbation-based Iterative Pruning), a novel double-view structured pruning method to optimize LLMs, which combines information from two different views: the unperturbed view and the perturbed view. With the calculation of gradient differences, PIP iteratively prunes those that struggle to distinguish between these two views. Our experiments show that PIP reduces the parameter count by approximately 20% while retaining over 85% of the original model's accuracy across varied benchmarks. In some cases, the performance of the pruned model is within 5% of the unpruned version, demonstrating PIP's ability to preserve key aspects of model effectiveness. Moreover, PIP consistently outperforms existing state-of-the-art (SOTA) structured pruning methods, establishing it as a leading technique for optimizing LLMs in environments with constrained resources. Our code is available at: https://github.com/caoyiiiiii/PIP.

The principle of rewarding a crowd for surprisingly common answers has been used in the literature for designing a number of truthful information elicitation mechanisms. A related method has also been proposed in the literature for better aggregation of crowd wisdom. Drawing a comparison between crowd based collective intelligence systems and large language models, we define the notion of 'surprisingly likely' textual response of a large language model. This notion is inspired by the surprisingly common principle, but tailored for text in a language model. Using benchmarks such as TruthfulQA and openly available LLMs: GPT-2 and LLaMA-2, we show that the surprisingly likely textual responses of large language models are more accurate in many cases compared to standard baselines. For example, we observe up to 24 percentage points aggregate improvement on TruthfulQA and up to 70 percentage points improvement on individual categories of questions in this benchmark. We also provide further analysis of the results, including the cases when surprisingly likely responses are less or not more accurate.

Evolutionary computation excels in complex optimization but demands deep domain knowledge, restricting its accessibility. Large Language Models (LLMs) offer a game-changing solution with their extensive knowledge and could democratize the optimization paradigm. Although LLMs possess significant capabilities, they may not be universally effective, particularly since evolutionary optimization encompasses multiple stages. It is therefore imperative to evaluate the suitability of LLMs as evolutionary optimizer (EVO). Thus, we establish a series of rigid standards to thoroughly examine the fidelity of LLM-based EVO output in different stages of evolutionary optimization and then introduce a robust error-correction mechanism to mitigate the output uncertainty. Furthermore, we explore a cost-efficient method that directly operates on entire populations with excellent effectiveness in contrast to individual-level optimization. Through extensive experiments, we rigorously validate the performance of LLMs as operators targeted for combinatorial problems. Our findings provide critical insights and valuable observations, advancing the understanding and application of LLM-based optimization.

Recent years have witnessed significant advancements in graph machine learning (GML), with its applications spanning numerous domains. However, the focus of GML has predominantly been on developing powerful models, often overlooking a crucial initial step: constructing suitable graphs from common data formats, such as tabular data. This construction process is fundamental to applying graphbased models, yet it remains largely understudied and lacks formalization. Our research aims to address this gap by formalizing the graph construction problem and proposing an effective solution. We identify two critical challenges to achieve this goal: 1. The absence of dedicated datasets to formalize and evaluate the effectiveness of graph construction methods, and 2. Existing automatic construction methods can only be applied to some specific cases, while tedious human engineering is required to generate high-quality graphs. To tackle these challenges, we present a two-fold contribution. First, we introduce a set of datasets to formalize and evaluate graph construction methods. Second, we propose an LLM-based solution, AutoG, automatically generating high-quality graph schemas without human intervention. The experimental results demonstrate that the quality of constructed graphs is critical to downstream task performance, and AutoG can generate high-quality graphs that rival those produced by human experts.