Text-to-SQL parsing and end-to-end question answering (E2E TQA) are two main approaches for Table-based Question Answering task. Despite success on multiple benchmarks, they have yet to be compared and their synergy remains unexplored. In this paper, we identify different strengths and weaknesses through evaluating state-of-the-art models on benchmark datasets: Text-to-SQL demonstrates superiority in handling questions involving arithmetic operations and long tables; E2E TQA excels in addressing ambiguous questions, non-standard table schema, and complex table contents. To combine both strengths, we propose a Synergistic Table-based Question Answering approach that integrate different models via answer selection, which is agnostic to any model types. Further experiments validate that ensembling models by either feature-based or LLM-based answer selector significantly improves the performance over individual models.

This report outlines our approach for the WMT24 Discourse-Level Literary Translation Task, focusing on the Chinese-English language pair in the Constrained Track. Translating literary texts poses significant challenges due to the nuanced meanings, idiomatic expressions, and intricate narrative structures inherent in such works. To address these challenges, we leveraged the Chinese-Llama2 model, specifically enhanced for this task through a combination of Continual Pre-training (CPT) and Supervised Fine-Tuning (SFT). Our methodology includes a novel Incremental Decoding framework, which ensures that each sentence is translated with consideration of its broader context, maintaining coherence and consistency throughout the text. This approach allows the model to capture long-range dependencies and stylistic elements, producing translations that faithfully preserve the original literary quality. Our experiments demonstrate significant improvements in both sentence-level and document-level BLEU scores, underscoring the effectiveness of our proposed framework in addressing the complexities of document-level literary translation.

Bug localization in Verilog code is a crucial and time-consuming task during the verification of hardware design. Since introduction, Large Language Models (LLMs) have showed their strong programming capabilities. However, no work has yet considered using LLMs for bug localization in Verilog code. This paper presents Location-is-Key, an opensource LLM solution to locate functional errors in Verilog snippets. LiK achieves high localization accuracy, with a pass@1 localization accuracy of 93.3% on our test dataset based on RTLLM, surpassing GPT-4's 77.9% and comparable to Claude-3.5's 90.8%. Additionally, the bug location obtained by LiK significantly improves GPT-3.5's bug repair efficiency (Functional pass@1 increased from 40.39% to 58.92%), highlighting the importance of bug localization in LLM-based Verilog debugging. Compared to existing methods, LiK only requires the design specification and the erroneous code snippet, without the need for testbenches, assertions, or any other EDA tools. This research demonstrates the feasibility of using LLMs for Verilog error localization, thus providing a new direction for automatic Verilog code debugging.

Auto-evaluation is crucial for assessing response quality and offering feedback for model development. Recent studies have explored training large language models (LLMs) as generative judges to evaluate and critique other models' outputs. In this work, we investigate the idea of learning from both positive and negative data with preference optimization to enhance the evaluation capabilities of LLM judges across an array of different use cases. We achieve this by employing three approaches to collect the preference pairs for different use cases, each aimed at improving our generative judge from a different perspective. Our comprehensive study over a wide range of benchmarks demonstrates the effectiveness of our method. In particular, our generative judge achieves the best performance on 10 out of 13 benchmarks, outperforming strong baselines like GPT-4o and specialized judge models. Further analysis show that our judge model robustly counters inherent biases such as position and length bias, flexibly adapts to any evaluation protocol specified by practitioners, and provides helpful language feedback for improving downstream generator models.

It's nearly two years since OpenAI released ChatGPT on an unsuspecting world, and the world, closely followed by the stock market, lost its mind. All over the place, people were wringing their hands wondering: What This Will Mean For [enter occupation, industry, business, institution]. Within academia, for example, humanities professors agonised about how they would henceforth be able to grade essays if students were using ChatGPT or similar technology to help write them. The answer, of course, is to come up with better ways of grading, because students will use these tools for the simple reason that it would be idiotic not to – just as it would be daft to do budgeting without spreadsheets. But universities are slow-moving beasts and even as I write, there are committees in many ivory towers solemnly trying to formulate "policies on AI use".

In the past week or so, we've had a logo upgrade, a big New York Times profile, and a Moncler outerwear collaboration from LoveFrom, Jony Ive and Marc Newson's San Francisco–headquartered design studio. The real news, though, is confirmation that LoveFrom is working with OpenAI's founder Sam Altman to build a secretive as-yet-unnamed AI device with investors including Laurene Powell Jobs' Emerson Collective, and Ive himself. The former Apple chief design officer is sometimes gently mocked for his obsession with seemingly small details, but when it comes to a potential mainstream human-AI interface, the man who has spent the past five years preoccupied with buttons--going so far as to create a five-volume history of garment fasteners--could be, in a somewhat inevitable way, the exact kind of person required to walk this particular tightrope of ethics and ambition. Details so far are scarce but revealing, at least where intentions are concerned. LoveFrom is designing "a product that uses AI to create a computing experience that is less socially disruptive than the iPhone."

Despite significant advancements in large language models (LLMs) that enhance robot agents' understanding and execution of natural language (NL) commands, ensuring the agents adhere to user-specified constraints remains challenging, particularly for complex commands and long-horizon tasks. To address this challenge, we present three key insights, equivalence voting, constrained decoding, and domain-specific fine-tuning, which significantly enhance LLM planners' capability in handling complex tasks. Equivalence voting ensures consistency by generating and sampling multiple Linear Temporal Logic (LTL) formulas from NL commands, grouping equivalent LTL formulas, and selecting the majority group of formulas as the final LTL formula. Constrained decoding then uses the generated LTL formula to enforce the autoregressive inference of plans, ensuring the generated plans conform to the LTL. Domain-specific fine-tuning customizes LLMs to produce safe and efficient plans within specific task domains. Our approach, Safe Efficient LLM Planner (SELP), combines these insights to create LLM planners to generate plans adhering to user commands with high confidence. We demonstrate the effectiveness and generalizability of SELP across different robot agents and tasks, including drone navigation and robot manipulation. For drone navigation tasks, SELP outperforms state-of-the-art planners by 10.8% in safety rate (i.e., finishing tasks conforming to NL commands) and by 19.8% in plan efficiency. For robot manipulation tasks, SELP achieves 20.4% improvement in safety rate. Our datasets for evaluating NL-to-LTL and robot task planning will be released in github.com/lt-asset/selp.

Recently, video-language understanding has achieved great success through large-scale pre-training. However, data scarcity remains a prevailing challenge. This study quantitatively reveals an "impossible trinity" among data quantity, diversity, and quality in pre-training datasets. Recent efforts seek to refine large-scale, diverse ASR datasets compromised by low quality through synthetic annotations. These methods successfully leverage useful information in multimodal video content (frames, tags, ASR transcripts, etc.) to refine the original annotations. Nevertheless, they struggle to mitigate noise within synthetic annotations and lack scalability as the dataset size expands. To address these issues, we introduce the Video DataFlywheel framework, which iteratively refines video annotations with improved noise control methods. For iterative refinement, we first leverage a video-language model to generate synthetic annotations, resulting in a refined dataset. Then, we pre-train on it and fine-tune on human refinement examples for a stronger model. These processes are repeated for continuous improvement. For noise control, we present AdaTaiLr, a novel noise control method that requires weaker assumptions on noise distribution, thereby proving more effective in large datasets with theoretical guarantees. The combination of iterative refinement and AdaTaiLr can achieve better scalability in video-language understanding. Extensive experiments show that our framework outperforms existing data refinement baselines, delivering a 3% performance boost and improving dataset quality with minimal diversity loss. Furthermore, our refined dataset facilitates significant improvements in various video-language understanding tasks, including video question answering and text-video retrieval.

Recent advancements in large language models (LLMs) have shown promising results in multilingual translation even with limited bilingual supervision. The major challenges are catastrophic forgetting and parameter interference for finetuning LLMs when provided parallel training data. To address these challenges, we propose LANDeRMT, a \textbf{L}anguage-\textbf{A}ware \textbf{N}euron \textbf{De}tecting and \textbf{R}outing framework that selectively finetunes LLMs to \textbf{M}achine \textbf{T}ranslation with diverse translation training data. In LANDeRMT, we evaluate the awareness of neurons to MT tasks and categorize them into language-general and language-specific neurons. This categorization enables selective parameter updates during finetuning, mitigating parameter interference and catastrophic forgetting issues. For the detected neurons, we further propose a conditional awareness-based routing mechanism to dynamically adjust language-general and language-specific capacity within LLMs, guided by translation signals. Experimental results demonstrate that the proposed LANDeRMT is very effective in learning translation knowledge, significantly improving translation quality over various strong baselines for multiple language pairs.

Accurately predicting passenger travel choices under train delays can provide interpretable insights into the redistribution of passenger flow, offering crucial decision support for emergency response and service recovery. However, the diversity of travel choices due to passenger heterogeneity and the sparsity of delay events leads to issues of data sparsity and sample imbalance in the travel choices dataset under metro delays. It is challenging to model this problem using traditional machine learning approaches, which typically rely on large, balanced datasets. Given the strengths of large language models (LLMs) in text processing, understanding, and their capabilities in small-sample and even zero-shot learning, this paper proposes a novel Passenger Travel Choice prediction framework under metro delays with the Large Language Model (DelayPTC-LLM). The well-designed prompting engineering is developed to guide the LLM in making and rationalizing predictions about travel choices, taking into account passenger heterogeneity and features of the delay events. Utilizing real-world data from Shenzhen Metro, including Automated Fare Collection (AFC) data and detailed delay logs, a comparative analysis of DelayPTC-LLM with traditional prediction models demonstrates the superior capability of LLMs in handling complex, sparse datasets commonly encountered under disruption of transportation systems. The results validate the advantages of DelayPTC-LLM in terms of predictive accuracy and its potential to provide actionable insights for big traffic data.