Hallucinated outputs from language models pose risks in the medical domain, especially for lay audiences making health-related decisions. Existing factuality evaluation methods, such as entailment- and question-answering-based (QA), struggle with plain language summary (PLS) generation due to elaborative explanation phenomenon, which introduces external content (e.g., definitions, background, examples) absent from the source document to enhance comprehension. To address this, we introduce PlainQAFact, a framework trained on a fine-grained, human-annotated dataset PlainFact, to evaluate the factuality of both source-simplified and elaboratively explained sentences. PlainQAFact first classifies factuality type and then assesses factuality using a retrieval-augmented QA-based scoring method. Our approach is lightweight and computationally efficient. Empirical results show that existing factuality metrics fail to effectively evaluate factuality in PLS, especially for elaborative explanations, whereas PlainQAFact achieves state-of-the-art performance. We further analyze its effectiveness across external knowledge sources, answer extraction strategies, overlap measures, and document granularity levels, refining its overall factuality assessment.

Unimodal vision models are known to rely on spurious correlations, but it remains unclear to what extent Multimodal Large Language Models (MLLMs) exhibit similar biases despite language supervision. In this paper, we investigate spurious bias in MLLMs and introduce SpurLens, a pipeline that leverages GPT-4 and open-set object detectors to automatically identify spurious visual cues without human supervision. Our findings reveal that spurious correlations cause two major failure modes in MLLMs: (1) over-reliance on spurious cues for object recognition, where removing these cues reduces accuracy, and (2) object hallucination, where spurious cues amplify the hallucination by over 10x. We validate our findings in various MLLMs and datasets. Beyond diagnosing these failures, we explore potential mitigation strategies, such as prompt ensembling and reasoning-based prompting, and conduct ablation studies to examine the root causes of spurious bias in MLLMs. By exposing the persistence of spurious correlations, our study calls for more rigorous evaluation methods and mitigation strategies to enhance the reliability of MLLMs.

Efficient long-context inference is critical as large language models (LLMs) adopt context windows of ranging from 128K to 1M tokens. However, the growing key-value (KV) cache and the high computational complexity of attention create significant bottlenecks in memory usage and latency. In this paper, we find that attention in diverse long-context tasks exhibits sparsity, and LLMs implicitly "know" which tokens can be dropped or evicted at the head level after the pre-filling stage. Based on this insight, we propose Self-Attention Guided Eviction~(SAGE-KV), a simple and effective KV eviction cache method for long-context inference. After prefilling, our method performs a one-time top-k selection at both the token and head levels to compress the KV cache, enabling efficient inference with the reduced cache. Evaluations on LongBench and three long-context LLMs (Llama3.1-8B-Instruct-128k, Llama3-8B-Prolong-512k-Instruct, and Qwen2.5-7B-Instruct-128k) show that SAGE-KV maintains accuracy comparable to full attention while significantly improving efficiency. Specifically, SAGE-KV achieves 4x higher memory efficiency with improved accuracy over the static KV cache selection method StreamLLM, and 2x higher memory efficiency with better accuracy than the dynamic KV cache selection method Quest.

Reinforcement Learning (RL) has demonstrated remarkable success in solving sequential decision-making problems. However, in real-world scenarios, RL agents often struggle to generalize when faced with unseen actions that were not encountered during training. Some previous works on zero-shot action generalization rely on large datasets of action observations to capture the behaviors of new actions, making them impractical for real-world applications. In this paper, we introduce a novel zero-shot framework, Action Generalization from Limited Observations (AGLO). Our framework has two main components: an action representation learning module and a policy learning module. The action representation learning module extracts discriminative embeddings of actions from limited observations, while the policy learning module leverages the learned action representations, along with augmented synthetic action representations, to learn a policy capable of handling tasks with unseen actions. The experimental results demonstrate that our framework significantly outperforms state-of-the-art methods for zero-shot action generalization across multiple benchmark tasks, showcasing its effectiveness in generalizing to new actions with minimal action observations.

This paper introduces a novel approach to Dialogue State Tracking (DST) that leverages Large Language Models (LLMs) to generate natural language descriptions of dialogue states, moving beyond traditional slot-value representations. Conventional DST methods struggle with open-domain dialogues and noisy inputs. Motivated by the generative capabilities of LLMs, our Natural Language DST (NL-DST) framework trains an LLM to directly synthesize human-readable state descriptions. We demonstrate through extensive experiments on MultiWOZ 2.1 and Taskmaster-1 datasets that NL-DST significantly outperforms rule-based and discriminative BERT-based DST baselines, as well as generative slot-filling GPT-2 DST models, in both Joint Goal Accuracy and Slot Accuracy. Ablation studies and human evaluations further validate the effectiveness of natural language state generation, highlighting its robustness to noise and enhanced interpretability. Our findings suggest that NL-DST offers a more flexible, accurate, and human-understandable approach to dialogue state tracking, paving the way for more robust and adaptable task-oriented dialogue systems.

Multi-party dialogue generation presents significant challenges due to the complex interplay of multiple speakers and interwoven conversational threads. Traditional approaches often fall short in capturing these complexities, particularly when relying on manually annotated dialogue relations. This paper introduces Speaker-Attentive LLM (SA-LLM), a novel generative model that leverages pre-trained Large Language Models (LLMs) and a speaker-aware contrastive learning strategy to address these challenges. SA-LLM incorporates a speaker-attributed input encoding and a contrastive learning objective to implicitly learn contextual coherence and speaker roles without explicit relation annotations. Extensive experiments on the Ubuntu IRC and Movie Dialogues datasets demonstrate that SA-LLM significantly outperforms state-of-the-art baselines in automatic and human evaluations, achieving superior performance in fluency, coherence, informativeness, and response diversity. Ablation studies and detailed error analyses further validate the effectiveness of the proposed speaker-attentive training approach, highlighting its robustness across different speaker roles and context lengths. The results underscore the potential of SA-LLM as a powerful and annotation-free solution for high-quality multi-party dialogue generation.

Field-Programmable Gate Arrays (FPGAs) are widely used in modern hardware design, yet writing Hardware Description Language (HDL) code for FPGA implementation remains labor-intensive and complex. Large Language Models (LLMs) have emerged as a promising tool for automating HDL generation, but existing benchmarks for LLM HDL code generation primarily evaluate functional correctness while overlooking the critical aspect of hardware resource efficiency. Moreover, current benchmarks lack diversity, failing to capture the broad range of real-world FPGA applications. To address these gaps, we introduce ResBench, the first resource-oriented benchmark explicitly designed to differentiate between resource-optimized and inefficient LLM-generated HDL. ResBench consists of 56 problems across 12 categories, covering applications from finite state machines to financial computing. Our evaluation framework systematically integrates FPGA resource constraints, with a primary focus on Lookup Table (LUT) usage, enabling a realistic assessment of hardware efficiency. Experimental results reveal substantial differences in resource utilization across LLMs, demonstrating ResBench's effectiveness in distinguishing models based on their ability to generate resource-optimized FPGA designs.

Large Language Models (LLMs) require alignment to become useful and safe conversational agents [Rafailov et al., 2023, Azar et al., 2023, Hong et al., 2024, Ethayarajh et al., 2024, Wu et al., 2024]. However, human preferences are diverse and nuanced, leading recent work to frame alignment as a multi-objective problem [Zhao et al., 2023, Shi et al., 2024] over a variety of desirable attributes and alignment objectives, for example, helpfulness, safety, honesty, and conciseness. Test time alignment [Mudgal et al., 2023] enables flexible control over the importance of different objectives at inference time without expensive retraining. This is a useful property as the alignment of an LLM can be varied to address a specific task, prompt, or interaction with a variety of users with diverse preferences [Sorensen et al., 2024b]. Existing methods for multi-objective alignment often formalize this problem through a weight vector that characterizes the relative importance of the objectives at deployment [Shi et al., 2024, Wang et al., 2024b,a, Rame et al., 2024]. In practice, the correct weighting of objectives is often unknown, leading to models that over-optimize specific alignment goals whilst under-prioritizing others. To address this problem, recent work has proposed several solutions, including treating weights as hyperparameters [Shi et al., 2024], learning specific weightings for different groups [Zhao et al.,

Large language models (LLMs), as a new generation of recommendation engines, possess powerful summarization and data analysis capabilities, surpassing traditional recommendation systems in both scope and performance. One promising application is investment recommendation. In this paper, we reveal a novel product bias in LLM investment recommendation, where LLMs exhibit systematic preferences for specific products. Such preferences can subtly influence user investment decisions, potentially leading to inflated valuations of products and financial bubbles, posing risks to both individual investors and market stability. To comprehensively study the product bias, we develop an automated pipeline to create a dataset of 567,000 samples across five asset classes (stocks, mutual funds, cryptocurrencies, savings, and portfolios). With this dataset, we present the bf first study on product bias in LLM investment recommendations. Our findings reveal that LLMs exhibit clear product preferences, such as certain stocks (e.g., `AAPL' from Apple and `MSFT' from Microsoft). Notably, this bias persists even after applying debiasing techniques. We urge AI researchers to take heed of the product bias in LLM investment recommendations and its implications, ensuring fairness and security in the digital space and market.

Transformer models have achieved remarkable success across various AI applications but face significant training costs. Low-bit training, such as INT8 training, can leverage computational units with higher throughput, and has already demonstrated its effectiveness on GPT2 models with block-level quantization. However, it struggles with modern Transformer variants incorporating GLU units. This is because those variants demonstrate complex distributions of activation outliers. To address the challenge, we propose Fallback Quantization, implementing mixed-precision GEMM that dynamically falls back 8-bit to 16-bit for activation blocks containing outliers. Experiments show that our approach is robustly competent in both fine-tuning and pretraining settings. Moreover, our method achieves a 1.57x end-to-end training speedup on RTX4090 GPUs.