Anningzhe Gao

Yuhao Du, Zhuo Li, Pengyu Cheng et al.

Despite the substantial advancements in artificial intelligence, large language models (LLMs) remain being challenged by generation safety. With adversarial jailbreaking prompts, one can effortlessly induce LLMs to output harmful content, causing unexpected negative social impacts. This vulnerability highlights the necessity for robust LLM red-teaming strategies to identify and mitigate such risks before large-scale application. To detect specific types of risks, we propose a novel red-teaming method that $\textbf{A}$ttacks LLMs with $\textbf{T}$arget $\textbf{Toxi}$c $\textbf{A}$nswers ($\textbf{Atoxia}$). Given a particular harmful answer, Atoxia generates a corresponding user query and a misleading answer opening to examine the internal defects of a given LLM. The proposed attacker is trained within a reinforcement learning scheme with the LLM outputting probability of the target answer as the reward. We verify the effectiveness of our method on various red-teaming benchmarks, such as AdvBench and HH-Harmless. The empirical results demonstrate that Atoxia can successfully detect safety risks in not only open-source models but also state-of-the-art black-box models such as GPT-4o.

Junying Chen, Xidong Wang, Ke Ji et al.

Adapting a language model into a specific domain, a.k.a `domain adaption', is a common practice when specialized knowledge, e.g. medicine, is not encapsulated in a general language model like Llama2. The challenge lies in the heterogeneity of data across the two training stages, as it varies in languages, genres, or formats. To tackle this and simplify the learning protocol, we propose to transform heterogeneous data, from the both pre-training and supervised stages, into a unified, simple input-output pair format. We validate the new protocol in the domains where proprietary LLMs like ChatGPT perform relatively poorly, such as Traditional Chinese Medicine. The developed model, HuatuoGPT-II, has shown state-of-the-art performance in Chinese medicine domain on a number of benchmarks, e.g. medical licensing exams. It even outperforms proprietary models like ChatGPT and GPT-4 in some aspects, especially in Traditional Chinese Medicine. Expert manual evaluations further validate HuatuoGPT-II's advantages over existing LLMs. Notably, HuatuoGPT-II was benchmarked in a fresh Chinese National Medical Licensing Examination where it achieved the best performance, showcasing not only its effectiveness but also its generalization capabilities.

Fei Yu, Anningzhe Gao, Benyou Wang

Large language models (LLMs) often struggle with maintaining accuracy throughout multiple multiple reasoning steps, especially in mathematical reasoning where an error in earlier steps can propagate to subsequent ones and it ultimately leading to an incorrect answer. To reduce error propagation, guided decoding is employed to direct the LM decoding on a step-by-step basis. We argue that in guided decoding, assessing the potential of an incomplete reasoning path can be more advantageous than simply ensuring per-step correctness, as the former approach leads towards a correct final answer. This transforms the task into a $\textit{value estimation}$ problem in planning. Inspired by the findings that $\textit{outcome supervision for guided decoding essentially acts as a value model}$, we propose Outcome-supervised Value Model (OVM) that employs outcome supervision for training a value model, which prioritizes steps that lead to accurate conclusions. Furthermore, the OVM eliminates the need for labor-intensive annotations of step-level correctness, thereby significantly enhancing its scalability. Our experiments on two multi-step mathematical reasoning datasets, GSM8K and Game of 24, demonstrate the superior performance of the OVM model. Notably, in GSM8K, our $\textbf{OVM-7B model achieves state-of-the-art results among LLMs up to 13B parameters}$; especially it does not utilize GPT-4 or code execution. These findings offer a novel perspective on the role of outcome supervision in training value models for multi-step reasoning tasks and provide theoretical justification for its advantage in value estimation for guided decoding.

Junying Chen, Chi Gui, Anningzhe Gao et al.

The field of medical diagnosis has undergone a significant transformation with the advent of large language models (LLMs), yet the challenges of interpretability within these models remain largely unaddressed. This study introduces Chain-of-Diagnosis (CoD) to enhance the interpretability of LLM-based medical diagnostics. CoD transforms the diagnostic process into a diagnostic chain that mirrors a physician's thought process, providing a transparent reasoning pathway. Additionally, CoD outputs the disease confidence distribution to ensure transparency in decision-making. This interpretability makes model diagnostics controllable and aids in identifying critical symptoms for inquiry through the entropy reduction of confidences. With CoD, we developed DiagnosisGPT, capable of diagnosing 9604 diseases. Experimental results demonstrate that DiagnosisGPT outperforms other LLMs on diagnostic benchmarks. Moreover, DiagnosisGPT provides interpretability while ensuring controllability in diagnostic rigor.

Wentao Ge, Shunian Chen, Guiming Hardy Chen et al.

Multimodal large language models (MLLMs) have broadened the scope of AI applications. Existing automatic evaluation methodologies for MLLMs are mainly limited in evaluating queries without considering user experiences, inadequately addressing the nuances of creative and associative multimodal tasks. However, the open-ended and subjective nature of such tasks poses a significant challenge to the evaluation methodology, where it is difficult to define the ground-truth answers for them. To this end, in our paper, we propose a new evaluation paradigm for MLLMs, which is evaluating MLLMs with per-sample criteria using potent MLLM as the judge. To validate the feasibility and effectiveness of this paradigm, we design a benchmark, dubbed MLLM-Bench, by curating the evaluation samples across six comprehensive cognitive levels. We benchmark 21 popular MLLMs in a pairwise-comparison fashion, showing diverse performance across models. Moreover, the validity of our benchmark manifests itself in reaching 88.02% agreement with human evaluation. We contend that the proposed paradigm explores the potential of MLLMs as effective evaluation tools with the help of per-sample criteria. See online leaderboard at \url{https://mllm-bench.llmzoo.com}.

Chen Zhang, Dading Chong, Feng Jiang et al.

In natural human-to-human conversations, participants often receive feedback signals from one another based on their follow-up reactions. These reactions can include verbal responses, facial expressions, changes in emotional state, and other non-verbal cues. Similarly, in human-machine interactions, the machine can leverage the user's follow-up utterances as feedback signals to assess whether it has appropriately addressed the user's request. Therefore, we propose using the likelihood of follow-up utterances as rewards to differentiate preferred responses from less favored ones, without relying on human or commercial LLM-based preference annotations. Our proposed reward mechanism, ``Follow-up Likelihood as Reward" (FLR), matches the performance of strong reward models trained on large-scale human or GPT-4 annotated data on 8 pairwise-preference and 4 rating-based benchmarks. Building upon the FLR mechanism, we propose to automatically mine preference data from the online generations of a base policy model. The preference data are subsequently used to boost the helpfulness of the base model through direct alignment from preference (DAP) methods, such as direct preference optimization (DPO). Lastly, we demonstrate that fine-tuning the language model that provides follow-up likelihood with natural language feedback significantly enhances FLR's performance on reward modeling benchmarks and effectiveness in aligning the base policy model's helpfulness.

Xuhan Huang, Qingning Shen, Yan Hu et al.

Large Language Models (LLMs) have demonstrated strong performance across various natural language processing tasks, yet their proficiency in mathematical reasoning remains a key challenge. Addressing the gap between natural and mathematical language requires advanced reasoning capabilities, approaching those of Artificial General Intelligence (AGI). However, the evaluation remains challenging, as perfectly representing reality is inherently elusive, and traditional methods like manual or direct comparison of mathematical statements (Ramamonjison et al., 2023) are insufficient for assessing true modeling ability. We propose a process-oriented framework to evaluate LLMs' ability to construct mathematical models, using solvers to compare outputs with ground truth. Introducing Mamo, a benchmark with 1,209 questions covering ordinary differential equations, linear programming, and mixed-integer linear programming, we enable automatic evaluation of modeling accuracy. The results show that existing LLMs struggle with complex mathematical modeling tasks, with larger models demonstrating superior performance, while open-source models remain competitive in simpler cases but still fall short of proprietary models in more challenging problems.

Anningzhe Gao, Shan Dai, Yan Hu

Irregular and asynchronous event sequences are prevalent in many domains, such as social media, finance, and healthcare. Traditional temporal point processes (TPPs), like Hawkes processes, often struggle to model mutual inhibition and nonlinearity effectively. While recent neural network models, including RNNs and Transformers, address some of these issues, they still face challenges with long-term dependencies and computational efficiency. In this paper, we introduce the Mamba Hawkes Process (MHP), which leverages the Mamba state space architecture to capture long-range dependencies and dynamic event interactions. Our results show that MHP outperforms existing models across various datasets. Additionally, we propose the Mamba Hawkes Process Extension (MHP-E), which combines Mamba and Transformer models to enhance predictive capabilities. We present the novel application of the Mamba architecture to Hawkes processes, a flexible and extensible model structure, and a theoretical analysis of the synergy between state space models and Hawkes processes. Experimental results demonstrate the superior performance of both MHP and MHP-E, advancing the field of temporal point process modeling.

Zhuo Li, Yuege Feng, Dandan Guo et al.

The reward model (RM) plays a crucial role in aligning Large Language Models (LLMs) with human preferences through Reinforcement Learning, where the Bradley-Terry (BT) objective has been recognized as simple yet powerful, specifically for pairwise preference learning. However, BT-based RMs often struggle to effectively distinguish between similar preference responses, leading to insufficient separation between preferred and non-preferred outputs. Consequently, they may easily overfit easy samples and cannot generalize well to Out-Of-Distribution (OOD) samples, resulting in suboptimal performance. To address these challenges, this paper introduces an effective enhancement to BT-based RMs through an adaptive margin mechanism. Specifically, we design to dynamically adjust the RM focus on more challenging samples through margins, based on both semantic similarity and model-predicted reward differences, which is approached from a distributional perspective solvable with Optimal Transport (OT). By incorporating these factors into a principled OT cost matrix design, our adaptive margin enables the RM to better capture distributional differences between chosen and rejected responses, yielding significant improvements in performance, convergence speed, and generalization capabilities. Experimental results across multiple benchmarks demonstrate that our method outperforms several existing RM techniques, showcasing enhanced performance in both In-Distribution (ID) and OOD settings. Moreover, RLHF experiments support our practical effectiveness in better aligning LLMs with human preferences. Our code is available at https://github.com/BIRlz/APLOT

Wenya Xie, Qingying Xiao, Yu Zheng et al.

The recent success of Large Language Models (LLMs) has had a significant impact on the healthcare field, providing patients with medical advice, diagnostic information, and more. However, due to a lack of professional medical knowledge, patients are easily misled by generated erroneous information from LLMs, which may result in serious medical problems. To address this issue, we focus on tuning the LLMs to be medical assistants who collaborate with more experienced doctors. We first conduct a two-stage survey by inspiration-feedback to gain a broad understanding of the real needs of doctors for medical assistants. Based on this, we construct a Chinese medical dataset called DoctorFLAN to support the entire workflow of doctors, which includes 92K Q\&A samples from 22 tasks and 27 specialists. Moreover, we evaluate LLMs in doctor-oriented scenarios by constructing the DoctorFLAN-\textit{test} containing 550 single-turn Q\&A and DotaBench containing 74 multi-turn conversations. The evaluation results indicate that being a medical assistant still poses challenges for existing open-source models, but DoctorFLAN can help them significantly. It demonstrates that the doctor-oriented dataset and benchmarks we construct can complement existing patient-oriented work and better promote medical LLMs research.

Yuhao Du, Zhuo Li, Pengyu Cheng et al.

Reinforcement Learning from Human Feedback (RLHF) is crucial for aligning Large Language Models (LLMs) with human values. However, RLHF has been continuously challenged by its high complexity in implementation and computation consumption. Even with recent simplifications, such as Direct Preference Optimization (DPO) and Advantage Leftover Lunch (A-LoL), the problems of over-fitting and training instability remain hindering the alignment process from the expected optimal performance. To address the existing challenges, we propose a novel simplification of RLHF from the perspective of variational inference, called $\textbf{V}$ariational $\textbf{A}$lignment with $\textbf{R}$e-weighting ($\textbf{VAR}$). More specifically, by directly minimizing the distribution gap between the learning LLM policy and the optimal solution of RLHF, we transform the alignment objective into a reward-driven re-weighted supervised fine-tuning (SFT) form, which only requires minor adjustment on the SFT loss to obtain noticeable improvement on training stability and effectiveness. On comprehensive alignment and generation benchmarks, our VAR method has numerically achieved competitive performance in LLM alignment helpfulness and harmlessness.

Anningzhe Gao, Shan Dai

Temporal Point Processes (TPPs), especially Hawkes Process are commonly used for modeling asynchronous event sequences data such as financial transactions and user behaviors in social networks. Due to the strong fitting ability of neural networks, various neural Temporal Point Processes are proposed, among which the Neural Hawkes Processes based on self-attention such as Transformer Hawkes Process (THP) achieve distinct performance improvement. Although the THP has gained increasing studies, it still suffers from the {sequence prediction issue}, i.e., training on history sequences and inferencing about the future, which is a prevalent paradigm in realistic sequence analysis tasks. What's more, conventional THP and its variants simply adopt initial sinusoid embedding in transformers, which shows performance sensitivity to temporal change or noise in sequence data analysis by our empirical study. To deal with the problems, we propose a new Rotary Position Embedding-based THP (RoTHP) architecture in this paper. Notably, we show the translation invariance property and {sequence prediction flexibility} of our RoTHP induced by the {relative time embeddings} when coupled with Hawkes process theoretically. Furthermore, we demonstrate empirically that our RoTHP can be better generalized in sequence data scenarios with timestamp translations and in sequence prediction tasks.