While textless Spoken Language Models (SLMs) have shown potential in end-to-end speech-to-speech modeling, they still lag behind text-based Large Language Models (LLMs) in terms of semantic coherence and relevance. This work introduces the Align-SLM framework, which leverages preference optimization inspired by Reinforcement Learning with AI Feedback (RLAIF) to enhance the semantic understanding of SLMs. Our approach generates multiple speech continuations from a given prompt and uses semantic metrics to create preference data for Direct Preference Optimization (DPO). We evaluate the framework using ZeroSpeech 2021 benchmarks for lexical and syntactic modeling, the spoken version of the StoryCloze dataset for semantic coherence, and other speech generation metrics, including the GPT4-o score and human evaluation. Experimental results show that our method achieves state-of-the-art performance for SLMs on most benchmarks, highlighting the importance of preference optimization to improve the semantics of SLMs.

Mathematical theorem proving is an important testbed for large language models' deep and abstract reasoning capability. This paper focuses on improving LLMs' ability to write proofs in formal languages that permit automated proof verification/evaluation. Most previous results provide human-written lemmas to the theorem prover, which is an arguably oversimplified setting that does not sufficiently test the provers' planning and decomposition capabilities. Instead, we work in a more natural setup where the lemmas that are directly relevant to the theorem are not given to the theorem prover at test time. We design an RL-based training algorithm that encourages the model to decompose a theorem into lemmas, prove the lemmas, and then prove the theorem by using the lemmas. Our reward mechanism is inspired by how mathematicians train themselves: even if a theorem is too challenging to be proved by the current model, a positive reward is still given to the model for any correct and novel lemmas that are proposed and proved in this process. During training, our model proposes and proves lemmas that are not in the training dataset. In fact, these newly-proposed correct lemmas consist of 37.7% of the training replay buffer when we train on the dataset extracted from Archive of Formal Proofs (AFP). The model trained by our RL algorithm outperforms that trained by supervised finetuning, improving the pass rate from 40.8% to 45.5% on AFP test set, and from 36.5% to 39.5% on an out-of-distribution test set.

Large language models (LLMs) are emerging as few-shot learners capable of handling a variety of tasks, including comprehension, planning, reasoning, question answering, arithmetic calculations, and more. At the core of these capabilities is LLMs' proficiency in representing and understanding structural or semi-structural data, such as tables and graphs. Numerous studies have demonstrated that reasoning on tabular data or graphs is not only feasible for LLMs but also gives a promising research direction which treats these data as in-context data. The lightweight and human readable characteristics of in-context database can potentially make it an alternative for the traditional database in typical RAG (Retrieval Augmented Generation) settings. However, almost all current work focuses on static in-context data, which does not allow dynamic update. In this paper, to enable dynamic database update, delta encoding of database is proposed. We explore how data stored in traditional RDBMS can be encoded as in-context text and evaluate LLMs' proficiency for CRUD (Create, Read, Update and Delete) operations on in-context databases. A benchmark named InConDB is presented and extensive experiments are conducted to show the performance of different language models in enabling in-context database by varying the database encoding method, prompting method, operation type and input data distribution, revealing both the proficiency and limitations.

When an LLM's inference is performed with a positive temperature, posing the same problem repeatedly will yield a distribution across the possible answers. If the LLM performs well, we would expect most of the probability mass to lie on the correct answer; if it performs poorly, we might expect the distribution to be more uniform across all the answers. However, this intuition does not always hold. To better understand the actual behavior of LLMs, we provide several detailed examples in Section 2. In Section 3, we perform a more comprehensive analysis at scale and use the results to suggest a taxonomy of LLMs.

As large language models (LLMs) become increasingly powerful, traditional evaluation metrics tend to saturate, making it challenging to distinguish between models based on their performance. We propose a general method to transform existing LLM evaluations into a series of progressively more difficult tasks. These enhanced evaluations emphasize reasoning capabilities and can reveal relative performance differences that are not apparent in the original assessments. To demonstrate the effectiveness of our approach, we create a new multiple-choice test corpus, extend it into a family of evaluations, and assess a collection of LLMs. Our results offer insights into the comparative reasoning abilities of these models, particularly highlighting distinctions between OpenAI's o1-preview and Google's gemini-pro-1.5-002.

Code translation aims to convert a program from one programming language (PL) to another. This long-standing software engineering task is crucial for modernizing legacy systems, ensuring cross-platform compatibility, enhancing performance, and more. However, automating this process remains challenging due to many syntactic and semantic differences between PLs. Recent studies show that even advanced techniques such as large language models (LLMs), especially open-source LLMs, still struggle with the task. Currently, code LLMs are trained with source code from multiple programming languages, thus presenting multilingual capabilities. In this paper, we investigate whether such multilingual capabilities can be harnessed to enhance code translation. To achieve this goal, we introduce InterTrans, an LLM-based automated code translation approach that, in contrast to existing approaches, leverages intermediate translations across PLs to bridge the syntactic and semantic gaps between source and target PLs. InterTrans contains two stages. It first utilizes a novel Tree of Code Translation (ToCT) algorithm to plan transitive intermediate translation sequences between a given source and target PL, then validates them in a specific order. We evaluate InterTrans with three open LLMs on three benchmarks (i.e., CodeNet, HumanEval-X, and TransCoder) involving six PLs. Results show an absolute improvement between 18.3% to 43.3% in Computation Accuracy (CA) for InterTrans over Direct Translation with 10 attempts. The best-performing variant of InterTrans (with Magicoder LLM) achieved an average CA of 87.3%-95.4% on three benchmarks.

In this report, we argue that there is a realistic possibility that some AI systems will be conscious and/or robustly agentic in the near future. That means that the prospect of AI welfare and moral patienthood -- of AI systems with their own interests and moral significance -- is no longer an issue only for sci-fi or the distant future. It is an issue for the near future, and AI companies and other actors have a responsibility to start taking it seriously. We also recommend three early steps that AI companies and other actors can take: They can (1) acknowledge that AI welfare is an important and difficult issue (and ensure that language model outputs do the same), (2) start assessing AI systems for evidence of consciousness and robust agency, and (3) prepare policies and procedures for treating AI systems with an appropriate level of moral concern. To be clear, our argument in this report is not that AI systems definitely are -- or will be -- conscious, robustly agentic, or otherwise morally significant. Instead, our argument is that there is substantial uncertainty about these possibilities, and so we need to improve our understanding of AI welfare and our ability to make wise decisions about this issue. Otherwise there is a significant risk that we will mishandle decisions about AI welfare, mistakenly harming AI systems that matter morally and/or mistakenly caring for AI systems that do not.

Large language models (LLMs) have demonstrated a remarkable ability to serve as general-purpose tools for various language-based tasks. Recent works have demonstrated that the efficacy of such models can be improved through iterative dialog between multiple models, frequently referred to as multi-agent debate (MAD). While debate shows promise as a means of improving model efficacy, most works in this area treat debate as an emergent behavior, rather than a learned behavior. In doing so, current debate frameworks rely on collaborative behaviors to have been sufficiently trained into off-the-shelf models. To address this limitation, we propose ACC-Debate, an Actor-Critic based learning framework to produce a two-agent team specialized in debate. We demonstrate that ACC-Debate outperforms SotA debate techniques on a wide array of benchmarks. Recently, large language models (LLMs) have rapidly become a cornerstone in various applications, redefining how we process and generate language at scale (Thirunavukarasu et al., 2023; Hadi et al., 2023; Jiang et al., 2024). Their ability to handle diverse tasks, from translation (Zhu et al., 2024; Otter et al., 2020) to answering complex questions (Zhang et al., 2024; Hao et al., 2024; Havrilla et al., 2024), has attracted the attention of both industry as well as academia. However, despite these advancements, LLMs still exhibit notable weaknesses, particularly when it comes to answering factual questions and reasoning (Tonmoy et al., 2024; Rawte et al., 2023; Huang et al., 2023). To address these limitations, several techniques have been proposed, such as Chain-of-Thought (CoT) prompting (Wei et al., 2022), self-reflection (Ji et al., 2023; Shinn et al., 2023), and multiagent debate (MAD) (Du et al., 2023), to name a few. These approaches aim to improve the reasoning abilities of LLMs by guiding them toward more accurate answers through structured thinking or discourse. However, the majority of these techniques do not involve training the model specifically for these tasks but instead rely on zero-shot or few-shot capabilities.

Follow-up conversations with virtual assistants (VAs) enable a user to seamlessly interact with a VA without the need to repeatedly invoke it using a keyword (after the first query). Therefore, accurate Device-directed Speech Detection (DDSD) from the follow-up queries is critical for enabling naturalistic user experience. To this end, we explore the notion of Large Language Models (LLMs) and model the first query when making inference about the follow-ups (based on the ASR-decoded text), via prompting of a pretrained LLM, or by adapting a binary classifier on top of the LLM. In doing so, we also exploit the ASR uncertainty when designing the LLM prompts. We show on the real-world dataset of follow-up conversations that this approach yields large gains (20-40% reduction in false alarms at 10% fixed false rejects) due to the joint modeling of the previous speech context and ASR uncertainty, compared to when follow-ups are modeled alone.

Code translation transforms programs from one programming language (PL) to another. Several rule-based transpilers have been designed to automate code translation between different pairs of PLs. However, the rules can become obsolete as the PLs evolve and cannot generalize to other PLs. Recent studies have explored the automation of code translation using Large Language Models (LLMs). One key observation is that such techniques may work well for crafted benchmarks but fail to generalize to the scale and complexity of real-world projects with dependencies, custom types, PL-specific features, etc. We propose AlphaTrans, a neuro-symbolic approach to automate repository-level code translation. AlphaTrans translates both source and test code, and employs multiple levels of validation to ensure the translation preserves the functionality of the source program. To break down the problem for LLMs, AlphaTrans leverages program analysis to decompose the program into fragments and translates them in the reverse call order. We leveraged AlphaTrans to translate ten real-world open-source projects consisting of <836, 8575, 2719> classes, methods, and tests. AlphaTrans translated the entire repository of these projects consisting of 6899 source code fragments. 99.1% of the translated code fragments are syntactically correct, and AlphaTrans validates the translations' runtime behavior and functional correctness for 25.8%. On average, the integrated translation and validation take 36 hours to translate a project, showing its scalability in practice. For the syntactically or semantically incorrect translations, AlphaTrans generates a report including existing translation, stack trace, test errors, or assertion failures. We provided these artifacts to two developers to fix the translation bugs in four projects. They were able to fix the issues in 20.1 hours on average and achieve all passing tests.