More Like this

1. Faithful Chain-of-Thought Reasoning

   Lyu, Qing; Havaldar, Shreya; Stein, Adam; Zhang, Li; Rao, Delip; Wong, Eric; Apidianaki, Marianna; Callison-Burch, Chris (November 2023, The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL 2023))

   While Chain-of-Thought (CoT) prompting boosts Language Models’ (LM) performance on a gamut of complex reasoning tasks, the generated reasoning chain does not necessarily reflect how the model arrives at the answer (aka. faithfulness). We propose Faithful CoT, a reasoning framework involving two stages: Translation (Natural Language query → symbolic reasoning chain) and Problem Solving (reasoning chain → answer), using an LM and a deterministic solver respectively. This guarantees that the reasoning chain provides a faithful explanation of the final answer. Aside from interpretability, Faithful CoT also improves empirical performance: it outperforms standard CoT on 9 of 10 benchmarks from 4 diverse domains, with a relative accuracy gain of 6.3% on Math Word Problems (MWP), 3.4% on Planning, 5.5% on Multi-hop Question Answering (QA), and 21.4% on Relational Inference. Furthermore, with GPT-4 and Codex, it sets the new state-of-the-art few-shot performance on 7 datasets (with 95.0+ accuracy on 6 of them), showing a strong synergy between faithfulness and accuracy. 

   more » « less
2. EchoPrompt: Instructing the Model to Rephrase Queries for Improved In-context Learning

   Mekala, Raja_Sekhar_Reddy; Razeghi, Yasaman; Singh, Sameer (June 2024, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT))

   Language models are achieving impressive performance on various tasks by aggressively adopting inference-time prompting techniques,such as zero-shot and few-shot prompting. In this work, we introduce EchoPrompt, a simple yet effective approach that prompts the model to rephrase its queries before answering them. EchoPrompt is tailored for four scenarios, including standard and chain-of-thought prompting, in both zero-shot and few-shot settings. Experimental results show that EchoPrompt yields substantial improvementsacross all these settings for four families of causal language models. These improvements are observed across various numerical reasoning (e.g., GSM8K, SVAMP), reading comprehension (e.g., DROP), and logical reasoning (e.g., Coin flipping) tasks. On average, EchoPrompt improves the Zero-shot-CoT performance of code-davinci-002 by 5% in numerical tasks and 13% in reading comprehension tasks. Our empirical results indicate that EchoPrompt is an effective technique that enhances in-context learning performance. 

   more » « less
3. Measuring and Improving the Efficiency of Python Code Generated by LLMs Using CoT Prompting and Fine-Tuning

   https://doi.org/10.1109/ACCESS.2025.3585742  

   Jonnala, Ramya; Yang, Jeong; Lee, Young; Liang, Gongbo; Cao, Zechun (July 2025, IEEE Access)

   The burgeoning sophistication of Artificial Intelligence (AI) has catalyzed the rapid proliferation of Large Language Models (LLMs) within software development. These models are increasingly employed to automate the generation of functionally correct code, address complex computational problems, and facilitate the debugging of existing software systems. However, LLM-generated code often faces challenges due to inherent inefficiencies, including redundant logical structures, factually inconsistent content (hallucinations), and programming errors. To address this issue, our research rigorously evaluated the computational efficiency of Python code generated by three prominent LLMs: GPT-4o-Mini, GPT-3.5-Turbo, and GPT-4-Turbo. The evaluation metrics encompass execution time, memory utilization, and peak memory consumption, while maintaining the functional correctness of the generated code. Leveraging the EffiBench benchmark datasets within the Google Vertex AI Workbench environment, across a spectrum of machine configurations, the study implemented a consistent seed parameter to ensure experimental reproducibility. Furthermore, we investigated the impact of two distinct optimization strategies: Chain-of-Thought (CoT) prompting and model fine-tuning. Our findings reveal a significant enhancement in efficiency metrics for GPT-4o-Mini and GPT-3.5-Turbo when employing CoT prompting; however, this trend was not observed for GPT-4-Turbo. Based on its promising performance with CoT prompting, we selected the GPT-4o-Mini model for subsequent fine-tuning, aiming to further enhance both its computational efficiency and accuracy. However, contrary to our expectations, fine-tuning the GPT-4o-Mini model led to a discernible degradation in both its accuracy and computational efficiency. In conclusion, this study provides empirical evidence suggesting that the deployment of high-CPU machine configurations, in synergy with the utilization of the GPT-4o-Mini model and CoT prompting techniques, yields demonstrably more efficient and accurate LLM-generated Python code, particularly within computationally intensive application scenarios. 

   more » « less
4. Utilizing the CLASS Framework to Develop a Conversational AI Tutor for open-ended problems in ASSISTments

   Gilles, S; Worden, E; Luo, Z; Sonkar, S; Baranuik, R; Heffernan, N (January 2024, LAK 2024 (submitted, in review))

   We present a conversational AI tutor (CAIT) for the purpose of aiding students on middle school math problems. CAIT was created utilizing the CLASS framework, and it is an LLM fine-tuned on Vicuna using a conversational dataset created by prompting ChatGPT using problems and explanations in ASSISTments. CAIT is trained to generate scaffolding questions, provide hints, and correct mistakes on math problems. We find that CAIT identifies 60% of correct answers as correct, generates effective sub-problems 33% of the time, and has a positive sentiment 72% of the time, with the remaining 28% of interactions being neutral. This paper discusses the hurdles to further implementation of CAIT into ASSISTments, namely improved accuracy and efficacy of sub-problems, and establishes CAIT as a proof of concept that the CLASS framework can be applied to create an effective mathematics tutorbot. 

   more » « less
5. Language Models Don’t Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

   Turpin, M; Michael, J; Perez, E; Bowman, S R (February 2023, Advances in neural information processing systems)

   Large Language Models (LLMs) can achieve strong performance on many tasks by producing step-by-step reasoning before giving a final output, often referred to as chain-of-thought reasoning (CoT). It is tempting to interpret these CoT explanations as the LLM’s process for solving a task. This level of transparency into LLMs’ predictions would yield significant safety benefits. However, we find that CoT explanations can systematically misrepresent the true reason for a model’s prediction. We demonstrate that CoT explanations can be heavily influenced by adding biasing features to model inputs—e.g., by reordering the multiple-choice options in a few-shot prompt to make the answer always “(A)”—which models systematically fail to mention in their explanations. When we bias models toward incorrect answers, they frequently generate CoT explanations rationalizing those answers. This causes accuracy to drop by as much as 36% on a suite of 13 tasks from BIG-Bench Hard, when testing with GPT-3.5 from OpenAI and Claude 1.0 from Anthropic. On a social-bias task, model explanations justify giving answers in line with stereotypes without mentioning the influence of these social biases. Our findings indicate that CoT explanations can be plausible yet misleading, which risks increasing our trust in LLMs without guaranteeing their safety. Building more transparent and explainable systems will require either improving CoT faithfulness through targeted efforts or abandoning CoT in favor of alternative methods. 

   more » « less