The rapid development of large language models (LLMs) has provided significant support and opportunities for the advancement of domain-specific LLMs. However, fine-tuning these large models using Intangible Cultural Heritage (ICH) data inevitably faces challenges such as bias, incorrect knowledge inheritance, and catastrophic forgetting. To address these issues, we propose a novel training method that integrates a bidirectional chains of thought and a reward mechanism. This method is built upon ICH-Qwen, a large language model specifically designed for the field of intangible cultural heritage. The proposed method enables the model to not only perform forward reasoning but also enhances the accuracy of the generated answers by utilizing reverse questioning and reverse reasoning to activate the model's latent knowledge. Additionally, a reward mechanism is introduced during training to optimize the decision-making process. This mechanism improves the quality of the model's outputs through structural and content evaluations with different weighting schemes. We conduct comparative experiments on ICH-Qwen, with results demonstrating that our method outperforms 0-shot, step-by-step reasoning, knowledge distillation, and question augmentation methods in terms of accuracy, Bleu-4, and Rouge-L scores on the question-answering task. Furthermore, the paper highlights the effectiveness of combining the bidirectional chains of thought and reward mechanism through ablation experiments. In addition, a series of generalizability experiments are conducted, with results showing that the proposed method yields improvements on various domain-specific datasets and advanced models in areas such as Finance, Wikidata, and StrategyQA. This demonstrates that the method is adaptable to multiple domains and provides a valuable approach for model training in future applications across diverse fields.
In this paper, we introduce Rule-Guided Feedback (RGF), a framework designed to enhance Large Language Model (LLM) performance through structured rule adherence and strategic information seeking. RGF implements a teacher-student paradigm where rule-following is forced through established guidelines. Our framework employs a Teacher model that rigorously evaluates each student output against task-specific rules, providing constructive guidance rather than direct answers when detecting deviations. This iterative feedback loop serves two crucial purposes: maintaining solutions within defined constraints and encouraging proactive information seeking to resolve uncertainties. We evaluate RGF on diverse tasks including Checkmate-in-One puzzles, Sonnet Writing, Penguins-In-a-Table classification, GSM8k, and StrategyQA. Our findings suggest that structured feedback mechanisms can significantly enhance LLMs' performance across various domains.
Large Language Models (LLMs) are increasingly being used in real-world applications. However, concerns about the reliability of the content they generate persist, as it frequently deviates from factual correctness or exhibits deficiencies in logical reasoning. This paper proposes a novel decoding strategy aimed at enhancing both factual accuracy and inferential reasoning without requiring any modifications to the architecture or pre-trained parameters of LLMs. Our approach adjusts next-token probabilities by analyzing the trajectory of logits from lower to higher layers in Transformers and applying linear regression. We find that this Decoding by Logit Trajectory-based approach (DeLTa) effectively reinforces factuality and reasoning while mitigating incorrect generation. Experiments on TruthfulQA demonstrate that DeLTa attains up to a 4.9% improvement over the baseline. Furthermore, it enhances performance by up to 8.1% on StrategyQA and 7.3% on GSM8K, both of which demand strong reasoning capabilities.
Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic comparison of decision protocols is difficult because many studies alter multiple discussion parameters beyond the protocol. So far, it has been largely unknown how decision-making influences different tasks. This work systematically evaluates the impact of seven decision protocols (e.g., majority voting, unanimity consensus). We change only one variable at a time - the decision protocol - to analyze how different methods affect the collaboration between agents and measure differences in knowledge and reasoning tasks. Our results show that voting protocols improve performance by 13.2% in reasoning tasks and consensus protocols by 2.8% in knowledge tasks compared to other decision protocols. Increasing the number of agents improves performance, while more discussion rounds before voting reduce it. To improve decision-making by increasing answer diversity, we propose two new methods, All-Agents Drafting (AAD) and Collective Improvement (CI). Our methods improve task performance by up to 3.3% with AAD and up to 7.4% with CI. This work demonstrates the importance of decision-making in multi-agent debates beyond scaling.
This work introduces a novel paradigm for generalized In-Context Learning (ICL), termed Indirect In-Context Learning. In Indirect ICL, we explore demonstration selection strategies tailored for two distinct real-world scenarios: Mixture of Tasks and Noisy Demonstrations. We systematically evaluate the effectiveness of Influence Functions (IFs) as a selection tool for these settings, highlighting the potential for IFs to better capture the informativeness of examples within the demonstration pool. For the Mixture of Tasks setting, demonstrations are drawn from 28 diverse tasks, including MMLU, BigBench, StrategyQA, and CommonsenseQA. We demonstrate that combining BertScore-Recall (BSR) with an IF surrogate model can significantly improve performance, leading to average absolute accuracy gains of 0.37\% and 1.45\% for 3-shot and 5-shot setups when compared to traditional ICL metrics. In the Noisy Demonstrations setting, we examine scenarios where demonstrations might be mislabeled. Our experiments show that reweighting traditional ICL selectors (BSR and Cosine Similarity) with IF-based selectors boosts accuracy by an average of 2.90\% for Cosine Similarity and 2.94\% for BSR on noisy GLUE benchmarks. In sum, we propose a robust framework for demonstration selection that generalizes beyond traditional ICL, offering valuable insights into the role of IFs for Indirect ICL.
Chain of Thought (CoT) was introduced in recent research as a method for improving step-by-step reasoning in Large Language Models. However, CoT has limited applications such as its need for hand-crafted few-shot exemplar prompts and no capability to adjust itself to different queries. In this work, we propose a system to automatically generate rationales using CoT. Our method improves multi-step implicit reasoning capabilities by decomposing the implicit query into several explicit questions. This provides interpretability for the model, improving reasoning in weaker LLMs. We test our approach with two Q\&A datasets: StrategyQA and HotpotQA. We show an increase in accuracy with both, especially on StrategyQA. To facilitate further research in this field, the complete source code for this study has been made publicly available on GitHub: https://github.com/miralab-ai/autoreason.
Large language models demonstrated state-of-the-art results on various reasoning tasks when applying the chain-of-thought (CoT) prompting technique. CoT prompting guides the model into breaking tasks into a few intermediate steps and provides step-by-step demonstrations. However, solving complex reasoning tasks remains a challenge. In this paper, we propose a novel prompting strategy inspired by Dialectical Behavioral Therapy (DBT). DBT, a form of cognitive-behavioral therapy, aims to help individuals cope with stress by developing a system of reasoning. We applied DBT's basic concepts of shaping dialog to construct prompts and conducted experiments on different datasets and LLMs with various numbers of parameters. Our results show that prompts crafted with DBT techniques significantly improve results on smaller models, achieving a 7% increase in accuracy on the StrategyQA, 4.8% on Aqua dataset using 8b parameters model, and a 16.2% increase on the StrategyQA, 5.3% on GSM8K dataset with 14b parameters model.
Answer verification identifies correct solutions among candidates generated by large language models (LLMs). Current approaches typically train verifier models by labeling solutions as correct or incorrect based solely on whether the final answer matches the gold answer. However, this approach neglects any flawed rationale in the solution yielding the correct answer, undermining the verifier's ability to distinguish between sound and flawed rationales. We empirically show that in StrategyQA, only 19% of LLM-generated solutions with correct answers have valid rationales, thus leading to an unreliable verifier. Furthermore, we demonstrate that training a verifier on valid rationales significantly improves its ability to distinguish valid and flawed rationale. To make a better verifier without extra human supervision, we introduce REPS (Rationale Enhancement through Pairwise Selection), a method for selecting valid rationales from candidates by iteratively applying pairwise self-evaluation using the same LLM that generates the solutions. Verifiers trained on solutions selected by REPS outperform those trained using conventional training methods on three reasoning benchmarks (ARC-Challenge, DROP, and StrategyQA). Our results suggest that training reliable verifiers requires ensuring the validity of rationales in addition to the correctness of the final answers, which would be critical for models assisting humans in solving complex reasoning tasks.
In an era where large language models (LLMs) are increasingly integrated into a wide range of everyday applications, research into these models' behavior has surged. However, due to the novelty of the field, clear methodological guidelines are lacking. This raises concerns about the replicability and generalizability of insights gained from research on LLM behavior. In this study, we discuss the potential risk of a replication crisis and support our concerns with a series of replication experiments focused on prompt engineering techniques purported to influence reasoning abilities in LLMs. We tested GPT-3.5, GPT-4o, Gemini 1.5 Pro, Claude 3 Opus, Llama 3-8B, and Llama 3-70B, on the chain-of-thought, EmotionPrompting, ExpertPrompting, Sandbagging, as well as Re-Reading prompt engineering techniques, using manually double-checked subsets of reasoning benchmarks including CommonsenseQA, CRT, NumGLUE, ScienceQA, and StrategyQA. Our findings reveal a general lack of statistically significant differences across nearly all techniques tested, highlighting, among others, several methodological weaknesses in previous research. We propose a forward-looking approach that includes developing robust methodologies for evaluating LLMs, establishing sound benchmarks, and designing rigorous experimental frameworks to ensure accurate and reliable assessments of model outputs.
Large Language Models (LLMs) have revolutionized natural language processing, yet they struggle with inconsistent reasoning, particularly in novel domains and complex logical sequences. This research introduces Proof of Thought, a framework that enhances the reliability and transparency of LLM outputs. Our approach bridges LLM-generated ideas with formal logic verification, employing a custom interpreter to convert LLM outputs into First Order Logic constructs for theorem prover scrutiny. Central to our method is an intermediary JSON-based Domain-Specific Language, which by design balances precise logical structures with intuitive human concepts. This hybrid representation enables both rigorous validation and accessible human comprehension of LLM reasoning processes. Key contributions include a robust type system with sort management for enhanced logical integrity, explicit representation of rules for clear distinction between factual and inferential knowledge, and a flexible architecture that allows for easy extension to various domain-specific applications. We demonstrate Proof of Thought's effectiveness through benchmarking on StrategyQA and a novel multimodal reasoning task, showing improved performance in open-ended scenarios. By providing verifiable and interpretable results, our technique addresses critical needs for AI system accountability and sets a foundation for human-in-the-loop oversight in high-stakes domains.
This paper introduces rStar, a self-play mutual reasoning approach that significantly improves reasoning capabilities of small language models (SLMs) without fine-tuning or superior models. rStar decouples reasoning into a self-play mutual generation-discrimination process. First, a target SLM augments the Monte Carlo Tree Search (MCTS) with a rich set of human-like reasoning actions to construct higher quality reasoning trajectories. Next, another SLM, with capabilities similar to the target SLM, acts as a discriminator to verify each trajectory generated by the target SLM. The mutually agreed reasoning trajectories are considered mutual consistent, thus are more likely to be correct. Extensive experiments across five SLMs demonstrate rStar can effectively solve diverse reasoning problems, including GSM8K, GSM-Hard, MATH, SVAMP, and StrategyQA. Remarkably, rStar boosts GSM8K accuracy from 12.51% to 63.91% for LLaMA2-7B, from 36.46% to 81.88% for Mistral-7B, from 74.53% to 91.13% for LLaMA3-8B-Instruct. Code will be available at https://github.com/zhentingqi/rStar.
Retrieval-augmented generation resorts to content retrieved from external sources in order to leverage the performance of large language models in downstream tasks. The excessive volume of retrieved content, the possible dispersion of its parts, or their out of focus range may happen nevertheless to eventually have a detrimental rather than an incremental effect. To mitigate this issue and improve retrieval-augmented generation, we propose a method to refine the retrieved content before it is included in the prompt by resorting to meta-prompting optimization. Put to empirical test with the demanding multi-hop question answering task from the StrategyQA dataset, the evaluation results indicate that this method outperforms a similar retrieval-augmented system but without this method by over 30%.
Although LLMs have the potential to transform many fields, they still underperform humans in reasoning tasks. Existing methods induce the model to produce step-by-step calculations, but this research explores the question: Does making the LLM analyze the question improve its performance? We propose a novel prompting strategy called Question Analysis Prompting (QAP), in which the model is prompted to explain the question in $n$ words before solving. The value of $n$ influences the length of response generated by the model. QAP is evaluated on GPT 3.5 Turbo and GPT 4 Turbo on arithmetic datasets GSM8K, AQuA, and SAT and commonsense dataset StrategyQA. QAP is compared with other state-of-the-art prompts including Chain-of-Thought (CoT), Plan and Solve Prompting (PS+) and Take A Deep Breath (TADB). QAP outperforms all state-of-the-art prompts on AQuA and SAT datasets on both GPT3.5 and GPT4. QAP consistently ranks among the top-2 prompts on 75\% of the tests. A key factor of QAP performance can be attributed to response length, where detailed responses are beneficial when answering harder questions, but can negatively affect easy questions.
Large Language Models (LLMs) have demonstrated remarkable potential in handling complex reasoning tasks by generating step-by-step rationales.Some methods have proven effective in boosting accuracy by introducing extra verifiers to assess these paths. However, existing verifiers, typically trained on binary-labeled reasoning paths, fail to fully utilize the relative merits of intermediate steps, thereby limiting the effectiveness of the feedback provided. To overcome this limitation, we propose Tree-based Preference Learning Verifier (Tree-PLV), a novel approach that constructs reasoning trees via a best-first search algorithm and collects step-level paired data for preference training. Compared to traditional binary classification, step-level preferences more finely capture the nuances between reasoning steps, allowing for a more precise evaluation of the complete reasoning path. We empirically evaluate Tree-PLV across a range of arithmetic and commonsense reasoning tasks, where it significantly outperforms existing benchmarks. For instance, Tree-PLV achieved substantial performance gains over the Mistral-7B self-consistency baseline on GSM8K (67.55% to 82.79%), MATH (17.00% to 26.80%), CSQA (68.14% to 72.97%), and StrategyQA (82.86% to 83.25%).Additionally, our study explores the appropriate granularity for applying preference learning, revealing that step-level guidance provides feedback that better aligns with the evaluation of the reasoning process.
Mixture-of-Experts (MoE) has emerged as a prominent architecture for scaling model size while maintaining computational efficiency. In MoE, each token in the input sequence activates a different subset of experts determined by a routing mechanism. However, the unchosen experts in MoE models do not contribute to the output, potentially leading to underutilization of the model's capacity. In this work, we first conduct exploratory studies to demonstrate that increasing the number of activated experts does not necessarily improve and can even degrade the output quality. Then, we show that output distributions from an MoE model using different routing strategies substantially differ, indicating that different experts do not always act synergistically. Motivated by these findings, we propose Self-Contrast Mixture-of-Experts (SCMoE), a training-free strategy that utilizes unchosen experts in a self-contrast manner during inference. In SCMoE, the next-token probabilities are determined by contrasting the outputs from strong and weak activation using the same MoE model. Our method is conceptually simple and computationally lightweight, as it incurs minimal latency compared to greedy decoding. Experiments on several benchmarks (GSM8K, StrategyQA, MBPP and HumanEval) demonstrate that SCMoE can consistently enhance Mixtral 8x7B's reasoning capability across various domains. For example, it improves the accuracy on GSM8K from 61.79 to 66.94. Moreover, combining SCMoE with self-consistency yields additional gains, increasing major@20 accuracy from 75.59 to 78.31.
Large language models have been widely adopted in natural language processing, yet they face the challenge of generating unreliable content. Recent works aim to reduce misinformation and hallucinations by resorting to attribution as a means to provide evidence (i.e., citations). However, current attribution methods usually focus on the retrieval stage and automatic evaluation that neglect mirroring the citation mechanisms in human scholarly writing to bolster credibility. In this paper, we address these challenges by modelling the attribution task as preference learning and introducing an Automatic Preference Optimization (APO) framework. First, we create a curated collection for post-training with 6,330 examples by collecting and filtering from existing datasets. Second, considering the high cost of labelling preference data, we further propose an automatic method to synthesize attribution preference data resulting in 95,263 pairs. Moreover, inspired by the human citation process, we further propose a progressive preference optimization method by leveraging fine-grained information. Extensive experiments on three datasets (i.e., ASQA, StrategyQA, and ELI5) demonstrate that APO achieves state-of-the-art citation F1 with higher answer quality.
Knowledge graph question answering (KGQA) is a well-established field that seeks to provide factual answers to natural language (NL) questions by leveraging knowledge graphs (KGs). However, existing KGQA datasets suffer from two significant limitations: (1) no existing KGQA dataset requires commonsense reasoning to arrive at an answer and (2) existing KGQA datasets focus on popular entities for which large language models (LLMs) can directly answer without hallucinating and without leveraging the KG. In this work, we seek a novel KGQA dataset that supports commonsense reasoning and focuses on long-tail entities (e.g., non-mainstream and recent entities) where LLMs frequently hallucinate, and thus create the need for novel methodologies that leverage the KG for factual and attributable commonsense inference. We create a novel Commonsense Reasoning (CR) and Long-Tail (LT) KGQA dataset with two subtasks -- question answering and claim verification -- that address both limitations (1) and (2). We construct CR-LT-KGQA by building extensions to existing reasoning datasets StrategyQA and CREAK over Wikidata. While existing KGQA methods are not applicable due to their lack of commonsense inference support, baseline evaluation of LLMs on CR-LT KGQA demonstrate a high rate of hallucination. Thus, CR-LT KGQA poses significant challenges for hallucination-prone LLMs, hence paving the way for future commonsense KGQA research to provide accurate and factual answers for long-tail entities in the era of LLMs.
We propose a straightforward approach called Distillation Contrastive Decoding (DCD) to enhance the reasoning capabilities of Large Language Models (LLMs) during inference. In contrast to previous approaches that relied on smaller amateur models or analysis of hidden state differences, DCD employs Contrastive Chain-of-thought Prompting and advanced distillation techniques, including Dropout and Quantization. This approach effectively addresses the limitations of Contrastive Decoding (CD), which typically requires both an expert and an amateur model, thus increasing computational resource demands. By integrating contrastive prompts with distillation, DCD obviates the need for an amateur model and reduces memory usage. Our evaluations demonstrate that DCD significantly enhances LLM performance across a range of reasoning benchmarks, surpassing both CD and existing methods in the GSM8K and StrategyQA datasets.
While Language Agents have achieved promising success by placing Large Language Models at the core of a more versatile design that dynamically interacts with the external world, the existing approaches neglect the notion of uncertainty during these interactions. We present the Uncertainty-Aware Language Agent (UALA), a framework that orchestrates the interaction between the agent and the external world using uncertainty quantification. Compared with other well-known counterparts like ReAct, our extensive experiments across 3 representative tasks (HotpotQA, StrategyQA, MMLU) and various LLM sizes demonstrate that UALA brings a significant improvement of performance, while having a substantially lower reliance on the external world (i.e., reduced number of tool calls and tokens). Our analyses provide various insights including the great potential of UALA compared with agent fine-tuning, and underscore the unreliability of verbalised confidence of LLMs as a proxy for uncertainty.
Self-consistency (SC) has been a widely used decoding strategy for chain-of-thought reasoning. Despite bringing significant performance improvements across a variety of multi-step reasoning tasks, it is a high-cost method that requires multiple sampling with the preset size. In this paper, we propose a simple and scalable sampling process, \textbf{E}arly-Stopping \textbf{S}elf-\textbf{C}onsistency (ESC), to greatly reduce the cost of SC without sacrificing performance. On this basis, one control scheme for ESC is further derivated to dynamically choose the performance-cost balance for different tasks and models. To demonstrate ESC's effectiveness, we conducted extensive experiments on three popular categories of reasoning tasks: arithmetic, commonsense and symbolic reasoning over language models with varying scales. The empirical results show that ESC reduces the average number of sampling of chain-of-thought reasoning by a significant margin on six benchmarks, including MATH (-33.8%), GSM8K (-80.1%), StrategyQA (-76.8%), CommonsenseQA (-78.5%), Coin Flip (-84.2%) and Last Letters (-67.4%), while attaining comparable performances.