Intermediate reasoning or acting steps have successfully improved large language models (LLMs) for handling various downstream natural language processing (NLP) tasks.When applying LLMs for code generation, recent works mainly focus on directing the models to articulate intermediate natural-language reasoning steps, as in chain-of-thought (CoT) prompting, and then output code with the natural language or other structured intermediate steps. However, such output is not suitable for code translation or generation tasks since the standard CoT has different logical structures and forms of expression with the code. In this work, we introduce the universal code (UniCode) as the intermediate representation. It is a description of algorithm steps using a mix of conventions of programming languages, such as assignment operator, conditional operator, and loop. Hence, we collect an instruction dataset UniCoder-Instruct to train our model UniCoder on multi-task learning objectives. UniCoder-Instruct comprises natural-language questions, code solutions, and the corresponding universal code. The alignment between the intermediate universal code representation and the final code solution significantly improves the quality of the generated code. The experimental results demonstrate that UniCoder with the universal code significantly outperforms the previous prompting methods by a large margin, showcasing the effectiveness of the structural clues in pseudo-code.
论文检索
输入标题、作者或关键词，从 9,460 篇学术成果中精准定位
As a relative quality comparison of model responses, human and Large Language Model (LLM) preferences serve as common alignment goals in model fine-tuning and criteria in evaluation. Yet, these preferences merely reflect broad tendencies, resulting in less explainable and controllable models with potential safety risks. In this work, we dissect the preferences of human and 32 different LLMs to understand their quantitative composition, using annotations from real-world user-model conversations for a fine-grained, scenario-wise analysis. We find that humans are less sensitive to errors, favor responses that support their stances, and show clear dislike when models admit their limits. On the contrary, advanced LLMs like GPT-4-Turbo emphasize correctness, clarity, and harmlessness more. Additionally, LLMs of similar sizes tend to exhibit similar preferences, regardless of their training methods, and fine-tuning for alignment does not significantly alter the preferences of pretrained-only LLMs. Finally, we show that preference-based evaluation can be intentionally manipulated. In both training-free and training-based settings, aligning a model with the preferences of judges boosts scores, while injecting the least preferred properties lowers them. This results in notable score shifts: up to 0.59 on MT-Bench (1-10 scale) and 31.94 on AlpacaEval 2.0 (0-100 scale), highlighting the significant impact of this strategic adaptation. We have made all resources of this project publicly available.
Ensuring correctness is a pivotal aspect of software engineering. Among the various strategies available, software verification offers a definitive assurance of correctness. Nevertheless, writing verification proofs is resource-intensive and manpower-consuming, and there is a great need to automate this process. We introduce Selene in this paper, which is the first project-level automated proof benchmark constructed based on the real-world industrial-level operating system microkernel, seL4. Selene provides a comprehensive framework for end-to-end proof generation and a lightweight verification environment. Our experimental results with advanced large language models (LLMs), such as GPT-3.5-turbo and GPT-4, highlight the capabilities of LLMs in the domain of automated proof generation. Additionally, our further proposed augmentations indicate that the challenges presented by Selene can be mitigated in future research endeavors.
While recent advancements in speech language models have achieved significant progress, they face remarkable challenges in modeling the long acoustic sequences of neural audio codecs. In this paper, we introduce Generative Pre-trained Speech Transformer (GPST), a hierarchical transformer designed for efficient speech language modeling. GPST quantizes audio waveforms into two distinct types of discrete speech representations and integrates them within a hierarchical transformer architecture, allowing for a unified one-stage generation process and enhancing Hi-Res audio generation capabilities. By training on large corpora of speeches in an end-to-end unsupervised manner, GPST can generate syntactically consistent speech with diverse speaker identities. Given a brief 3-second prompt, GPST can produce natural and coherent personalized speech, demonstrating in-context learning abilities. Moreover, our approach can be easily extended to spoken cross-lingual speech generation by incorporating multi-lingual semantic tokens and universal acoustic tokens. Experimental results indicate that GPST significantly outperforms the existing speech language models in terms of word error rate, speech quality, and speaker similarity. See https://youngsheen.github.io/GPST/demo for demo samples.
Grammatical error correction (GEC) is a task dedicated to rectifying texts with minimal edits, which can be decoupled into two components: detection and correction. However, previous works have predominantly focused on direct correction, with no prior efforts to integrate both into a single model. Moreover, the exploration of the detection-correction paradigm by large language models (LLMs) remains underdeveloped. This paper introduces an integrated detection-correction structure, named DeCoGLM, based on the General Language Model (GLM). The detection phase employs a fault-tolerant detection template, while the correction phase leverages autoregressive mask infilling for localized error correction. Through the strategic organization of input tokens and modification of attention masks, we facilitate multi-task learning within a single model. Our model demonstrates competitive performance against the state-of-the-art models on English and Chinese GEC datasets. Further experiments present the effectiveness of the detection-correction structure in LLMs, suggesting a promising direction for GEC.
An Effective Pronunciation Assessment Approach Leveraging Hierarchical Transformers and Pre-training Strategies
PDF ↗Automatic pronunciation assessment (APA) manages to quantify a second language (L2) learner’s pronunciation proficiency in a target language by providing fine-grained feedback with multiple pronunciation aspect scores at various linguistic levels. Most existing efforts on APA typically parallelize the modeling process, namely predicting multiple aspect scores across various linguistic levels simultaneously. This inevitably makes both the hierarchy of linguistic units and the relatedness among the pronunciation aspects sidelined. Recognizing such a limitation, we in this paper first introduce HierTFR, a hierarchal APA method that jointly models the intrinsic structures of an utterance while considering the relatedness among the pronunciation aspects. We also propose a correlation-aware regularizer to strengthen the connection between the estimated scores and the human annotations. Furthermore, novel pre-training strategies tailored for different linguistic levels are put forward so as to facilitate better model initialization. An extensive set of empirical experiments conducted on the speechocean762 benchmark dataset suggest the feasibility and effectiveness of our approach in relation to several competitive baselines.
Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition
PDF ↗The development of multimodal models has significantly advanced multimodal sentiment analysis and emotion recognition. However, in real-world applications, the presence of various missing modality cases often leads to a degradation in the model’s performance. In this work, we propose a novel multimodal Transformer framework using prompt learning to address the issue of missing modalities. Our method introduces three types of prompts: generative prompts, missing-signal prompts, and missing-type prompts. These prompts enable the generation of missing modality features and facilitate the learning of intra- and inter-modality information. Through prompt learning, we achieve a substantial reduction in the number of trainable parameters. Our proposed method outperforms other methods significantly across all evaluation metrics. Extensive experiments and ablation studies are conducted to demonstrate the effectiveness and robustness of our method, showcasing its ability to effectively handle missing modalities. Codes are available at https://github.com/zrguo/MPLMM.
Large Language Models (LLMs) can play a vital role in psychotherapy by adeptly handling the crucial task of cognitive reframing and overcoming challenges such as shame, distrust, therapist skill variability, and resource scarcity. Previous LLMs in cognitive reframing mainly converted negative emotions to positive ones, but these approaches have limited efficacy, often not promoting clients’ self-discovery of alternative perspectives. In this paper, we unveil the Helping and Empowering through Adaptive Language in Mental Enhancement (HealMe) model. This novel cognitive reframing therapy method effectively addresses deep-rooted negative thoughts and fosters rational, balanced perspectives. Diverging from traditional LLM methods, HealMe employs empathetic dialogue based on psychotherapeutic frameworks. It systematically guides clients through distinguishing circumstances from feelings, brainstorming alternative viewpoints, and developing empathetic, actionable suggestions. Moreover, we adopt the first comprehensive and expertly crafted psychological evaluation metrics, specifically designed to rigorously assess the performance of cognitive reframing, in both AI-simulated dialogues and real-world therapeutic conversations. Experimental results show that our model outperforms others in terms of empathy, guidance, and logical coherence, demonstrating its effectiveness and potential positive impact on psychotherapy.
Persuasive dialogue requires multi-turn following and planning abilities to achieve the goal of persuading users, which is still challenging even for state-of-the-art large language models (LLMs). Previous works focus on retrieval-based models or generative models in a specific domain due to a lack of data across multiple domains. In this paper, we leverage GPT-4 to create the first multi-domain persuasive dialogue dataset DailyPersuasion. Then we propose a general method named PersuGPT to learn a persuasion model based on LLMs through intent-to-strategy reasoning, which summarizes the intent of user’s utterance and reasons next strategy to respond. Moreover, we design a simulation-based preference optimization, which utilizes a learned user model and our model to simulate next turns and estimate their rewards more accurately. Experimental results on two datasets indicate that our proposed method outperforms all baselines in terms of automatic evaluation metric Win-Rate and human evaluation. The code and data are available at https://persugpt.github.io.
LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression
PDF ↗In long context scenarios, large language models (LLMs) face three main challenges: higher computational cost, performance reduction, and position bias. Research indicates that LLM performance hinges on the density and position of key information in the input prompt. Inspired by these findings, we propose LongLLMLingua for prompt compression towards improving LLMs’ perception of the key information to simultaneously address the three challenges. Our extensive evaluation across various long context scenarios demonstrates that LongLLMLingua not only enhances performance but also significantly reduces costs and latency. For instance, in the NaturalQuestions benchmark, LongLLMLingua boosts performance by up to 21.4% with around 4x fewer tokens in GPT-3.5-Turbo, leading to substantial cost savings. It achieves a 94.0% cost reduction in the LooGLE benchmark. Moreover, when compressing prompts of about 10k tokens at ratios of 2x-6x, LongLLMLingua can accelerate end-to-end latency by 1.4x-2.6x.
We investigate intention detection in persuasive multi-turn dialogs employing the largest available Large Language Models (LLMs).Much of the prior research measures the intention detection capability of machine learning models without considering the conversational history.To evaluate LLMs’ intention detection capability in conversation, we modified the existing datasets of persuasive conversation and created datasets using a multiple-choice paradigm.It is crucial to consider others’ perspectives through their utterances when engaging in a persuasive conversation, especially when making a request or reply that is inconvenient for others.This feature makes the persuasive dialogue suitable for the dataset of measuring intention detection capability.We incorporate the concept of ‘face acts,’ which categorize how utterances affect mental states.This approach enables us to measure intention detection capability by focusing on crucial intentions and to conduct comprehensible analysis according to intention types.
Reinforcement learning with natural language action space often suffers from the curse of dimensionality due to the combinatorial nature of the natural language. Previous research leverages pretrained language models to capture action semantics and reduce the size of the action space. However, since pretrained models are typically trained on general corpora, there can be an unpredictable mismatch between the priors encoded in pretrained models and the characteristics of the specific RL environment. To address this issue, we propose Mutual-Information Regularized Policy Optimization, MIPO. MIPO enables implicit and dynamic reduction of the action space. Starting from the prior provided by the pretrained language model, our method dynamically adjusts the prior during the learning process based on the guidance of mutual information regularization. Theoretically, we demonstrate that this policy optimization process leads to the monotonic improvement on the mutual-information regularized RL objective. Empirically, we conduct experiments in various environments and demonstrate the effectiveness of MIPO.
IBSEN: Director-Actor Agent Collaboration for Controllable and Interactive Drama Script Generation
PDF ↗Large language models have demonstrated their capabilities in storyline creation and human-like character role-playing. Current language model agents mainly focus on reasonable behaviors from the level of individuals, and their behaviors might be hard to constraint on the level of the whole storyline. In this paper we introduce IBSEN, a director-actor coordinate agent framework that generates drama scripts and makes the plot played by agents more controllable. The director agent writes plot outlines that the user desires to see, instructs the actor agents to role-play their characters, and reschedules the plot when human players participate in the scenario to ensure the plot is progressing towards the objective. To evaluate the framework, we create a novel drama plot that involves several actor agents and check the interactions between them under the instruction of the director agent. Evaluation results show that our framework could generate complete, diverse drama scripts from only a rough outline of plot objectives, meanwhile maintaining the characteristics of characters in the drama. Our codes and prompts are available at https://github.com/OpenDFM/ibsen.
Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding
PDF ↗The digital landscape is rapidly evolving with an ever-increasing volume of online news, emphasizing the need for swift and precise analysis of complex events.We refer to the complex events composed of many news articles over an extended period as Temporal Complex Event (TCE). This paper proposes a novel approach using Large Language Models (LLMs) to systematically extract and analyze the event chain within TCE, characterized by their key points and timestamps. We establish a benchmark, named TCELongBench, to evaluate the proficiency of LLMs in handling temporal dynamics and understanding extensive text. This benchmark encompasses three distinct tasks - reading comprehension, temporal sequencing, and future event forecasting. In the experiment, we leverage retrieval-augmented generation (RAG) method and LLMs with long context window to deal with lengthy news articles of TCE. Our findings indicate that models with suitable retrievers exhibit comparable performance with those utilizing long context window.
Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model’s internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy.
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation
PDF ↗Simultaneous translation models play a crucial role in facilitating communication. However, existing research primarily focuses on text-to-text or speech-to-text models, necessitating additional cascade components to achieve speech-to-speech translation. These pipeline methods suffer from error propagation and accumulate delays in each cascade component, resulting in reduced synchronization between the speaker and listener. To overcome these challenges, we propose a novel non-autoregressive generation framework for simultaneous speech translation (NAST-S2x), which integrates speech-to-text and speech-to-speech tasks into a unified end-to-end framework.We develop a non-autoregressive decoder capable of concurrently generating multiple text or acoustic unit tokens upon receiving fixed-length speech chunks. The decoder can generate blank or repeated tokens and employ CTC decoding to dynamically adjust its latency. Experimental results show that NAST-S2x outperforms state-of-the-art models in both speech-to-text and speech-to-speech tasks. It achieves high-quality simultaneous interpretation within a delay of less than 3 seconds and provides a 28× decoding speedup in offline generation.
Dependency Transformer Grammars: Integrating Dependency Structures into Transformer Language Models
PDF ↗Syntactic Transformer language models aim to achieve better generalization through simultaneously modeling syntax trees and sentences. While prior work has been focusing on adding constituency-based structures to Transformers, we introduce Dependency Transformer Grammars (DTGs), a new class of Transformer language model with explicit dependency-based inductive bias. DTGs simulate dependency transition systems with constrained attention patterns by modifying attention masks, incorporate the stack information through relative positional encoding, and augment dependency arc representation with a combination of token embeddings and operation embeddings. When trained on a dataset of sentences annotated with dependency trees, DTGs achieve better generalization while maintaining comparable perplexity with Transformer language model baselines. DTGs also outperform recent constituency-based models, showing that dependency can better guide Transformer language models. Our code is released at https://github.com/zhaoyd1/Dep_Transformer_Grammars.
To mitigate the potential misuse of large language models (LLMs), recent research has developed watermarking algorithms, which restrict the generation process to leave an invisible trace for watermark detection. Due to the two-stage nature of the task, most studies evaluate the generation and detection separately, thereby presenting a challenge in unbiased, thorough, and applicable evaluations. In this paper, we introduce WaterBench, the first comprehensive benchmark for LLM watermarks, in which we design three crucial factors: (1) For benchmarking procedure, to ensure an apples-to-apples comparison, we first adjust each watermarking method’s hyper-parameter to reach the same watermarking strength, then jointly evaluate their generation and detection performance. (2) For task selection, we diversify the input and output length to form a five-category taxonomy, covering 9 tasks. (3) For evaluation metric, we adopt the GPT4-Judge for automatically evaluating the decline of instruction-following abilities after watermarking. We evaluate 4 open-source watermarks on 2 LLMs under 2 watermarking strengths and observe the common struggles for current methods on maintaining the generation quality. The code and data are available at https://github.com/THU-KEG/WaterBench.
Large language models (LLMs) are effective at answering questions that are clearly asked. However, when faced with ambiguous queries they can act unpredictably and produce incorrect outputs. This underscores the need for the development of intelligent agents capable of asking clarification questions to resolve ambiguities effectively. This capability requires complex understanding, state tracking, reasoning and planning over multiple conversational turns. However, directly measuring this can be challenging.In this paper, we offer a surrogate problem which assesses an LLMs’s capability to deduce an entity unknown to itself, but revealed to a judge, by asking the judge a series of queries. This entity-deducing game can serve as an evaluation framework to probe the conversational reasoning and planning capabilities of language models.We systematically evaluate various LLMs and discover significant differences in their performance on this task. We find that strong LLMs like GPT-4 outperform human players by a large margin. We further employ Behavior Cloning (BC) to examine whether a weaker model is capable of imitating a stronger model and generalizing to data or domains, using only the demonstrations from a stronger model. We finally propose to use Reinforcement Learning to enhance reasoning and planning capacity of Vicuna models through episodes of game playing, which lead to significant performance improvement. We hope that this problem offers insights into how autonomous agents could be trained to behave more intelligently in ambiguous circumstances.
In-context learning (ICL), which promotes inference with several demonstrations, has become a widespread paradigm to stimulate LLM capabilities for downstream tasks. Due to context length constraints, it cannot be further improved in spite of more training data, and general features directly from LLMs in ICL are not adaptive to the specific downstream task. In this paper, we propose a feature-adaptive and data-scalable in-context learning framework (FADS-ICL), which can leverage task-adaptive features to promote inference on the downstream task, with the supervision of beyond-context samples.Specifically, it first extracts general features of beyond-context samples via the LLM with ICL input form one by one, and introduces a task-specific modulator to perform feature refinement and prediction after fitting a specific downstream task. We conduct extensive experiments on FADS-ICL under varying data settings (4~128 shots) and LLM scale (0.8~70B) settings. Experimental results show that FADS-ICL consistently outperforms previous state-of-the-art methods by a significant margin under all settings, verifying the effectiveness and superiority of FADS-ICL. For example, under the 1.5B and 32 shots setting, FADS-ICL can achieve +14.3 average accuracy from feature adaptation over vanilla ICL on 10 datasets, with +6.2 average accuracy over the previous state-of-the-art method, and the performance can further improve with increasing training data.