Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thinking'' really helpful? To analyze this, we conducted a quantitative meta-analysis covering over 100 papers using CoT and ran our own evaluations of 20 datasets across 14 models. Our results show that CoT gives strong performance benefits primarily on tasks involving math or logic, with much smaller gains on other types of tasks. On MMLU, directly generating the answer without CoT leads to almost identical accuracy as CoT unless the question or model's response contains an equals sign, indicating symbolic operations and reasoning. Following this finding, we analyze the behavior of CoT on these problems by separating planning and execution and comparing against tool-augmented LLMs. Much of CoT's gain comes from improving symbolic execution, but it underperforms relative to using a symbolic solver. Our results indicate that CoT can be applied selectively, maintaining performance while saving inference costs. Furthermore, they suggest a need to move beyond prompt-based CoT to new paradigms that better leverage intermediate computation across the whole range of LLM applications.

Purpose: To develop and evaluate an automated system for extracting structured clinical information from unstructured radiology and pathology reports using open-weights large language models (LMs) and retrieval augmented generation (RAG), and to assess the effects of model configuration variables on extraction performance. Methods and Materials: The study utilized two datasets: 7,294 radiology reports annotated for Brain Tumor Reporting and Data System (BT-RADS) scores and 2,154 pathology reports annotated for isocitrate dehydrogenase (IDH) mutation status. An automated pipeline was developed to benchmark the performance of various LMs and RAG configurations. The impact of model size, quantization, prompting strategies, output formatting, and inference parameters was systematically evaluated. Results: The best performing models achieved over 98% accuracy in extracting BT-RADS scores from radiology reports and over 90% for IDH mutation status extraction from pathology reports. The top model being medical fine-tuned llama3. Larger, newer, and domain fine-tuned models consistently outperformed older and smaller models. Model quantization had minimal impact on performance. Few-shot prompting significantly improved accuracy. RAG improved performance for complex pathology reports but not for shorter radiology reports. Conclusions: Open LMs demonstrate significant potential for automated extraction of structured clinical data from unstructured clinical reports with local privacy-preserving application. Careful model selection, prompt engineering, and semi-automated optimization using annotated data are critical for optimal performance. These approaches could be reliable enough for practical use in research workflows, highlighting the potential for human-machine collaboration in healthcare data extraction.

We introduce a novel analysis that leverages linguistic minimal pairs to probe the internal linguistic representations of Large Language Models (LLMs). By measuring the similarity between LLM activation differences across minimal pairs, we quantify the and gain insight into the linguistic knowledge captured by LLMs. Our large-scale experiments, spanning 100+ LLMs and 150k minimal pairs in three languages, reveal properties of linguistic similarity from four key aspects: consistency across LLMs, relation to theoretical categorizations, dependency to semantic context, and cross-lingual alignment of relevant phenomena. Our findings suggest that 1) linguistic similarity is significantly influenced by training data exposure, leading to higher cross-LLM agreement in higher-resource languages. 2) Linguistic similarity strongly aligns with fine-grained theoretical linguistic categories but weakly with broader ones. 3) Linguistic similarity shows a weak correlation with semantic similarity, showing its context-dependent nature. 4) LLMs exhibit limited cross-lingual alignment in their understanding of relevant linguistic phenomena. This work demonstrates the potential of minimal pairs as a window into the neural representations of language in LLMs, shedding light on the relationship between LLMs and linguistic theory.

Large language models (LLMs) have significantly advanced natural language processing tasks, yet they are susceptible to generating inaccurate or unreliable responses, a phenomenon known as hallucination. In critical domains such as health and medicine, these hallucinations can pose serious risks. This paper introduces HALO, a novel framework designed to enhance the accuracy and reliability of medical question-answering (QA) systems by focusing on the detection and mitigation of hallucinations. Our approach generates multiple variations of a given query using LLMs and retrieves relevant information from external open knowledge bases to enrich the context. We utilize maximum marginal relevance scoring to prioritize the retrieved context, which is then provided to LLMs for answer generation, thereby reducing the risk of hallucinations. The integration of LangChain further streamlines this process, resulting in a notable and robust increase in the accuracy of both open-source and commercial LLMs, such as Llama-3.1 (from 44% to 65%) and ChatGPT (from 56% to 70%). This framework underscores the critical importance of addressing hallucinations in medical QA systems, ultimately improving clinical decision-making and patient care. The open-source HALO is available at: https://github.com/ResponsibleAILab/HALO.

This paper investigates the factuality of large language models (LLMs) as knowledge bases in the legal domain, in a realistic usage scenario: we allow for acceptable variations in the answer, and let the model abstain from answering when uncertain. First, we design a dataset of diverse factual questions about case law and legislation. We then use the dataset to evaluate several LLMs under different evaluation methods, including exact, alias, and fuzzy matching. Our results show that the performance improves significantly under the alias and fuzzy matching methods. Further, we explore the impact of abstaining and in-context examples, finding that both strategies enhance precision. Finally, we demonstrate that additional pre-training on legal documents, as seen with SaulLM, further improves factual precision from 63% to 81%.

Ensuring annotator quality in training and evaluation data is a key piece of machine learning in NLP. Tasks such as sentiment analysis and offensive speech detection are intrinsically subjective, creating a challenging scenario for traditional quality assessment approaches because it is hard to distinguish disagreement due to poor work from that due to differences of opinions between sincere annotators. With the goal of increasing diverse perspectives in annotation while ensuring consistency, we propose \texttt{ARTICLE}, an in-context learning (ICL) framework to estimate annotation quality through self-consistency. We evaluate this framework on two offensive speech datasets using multiple LLMs and compare its performance with traditional methods. Our findings indicate that \texttt{ARTICLE} can be used as a robust method for identifying reliable annotators, hence improving data quality.

The capability to efficiently search for objects in complex environments is fundamental for many real-world robot applications. Recent advances in open-vocabulary vision models have resulted in semantically-informed object navigation methods that allow a robot to search for an arbitrary object without prior training. However, these zero-shot methods have so far treated the environment as unknown for each consecutive query. In this paper we introduce a new benchmark for zero-shot multi-object navigation, allowing the robot to leverage information gathered from previous searches to more efficiently find new objects. To address this problem we build a reusable open-vocabulary feature map tailored for real-time object search. We further propose a probabilistic-semantic map update that mitigates common sources of errors in semantic feature extraction and leverage this semantic uncertainty for informed multi-object exploration. We evaluate our method on a set of object navigation tasks in both simulation as well as with a real robot, running in real-time on a Jetson Orin AGX. We demonstrate that it outperforms existing state-of-the-art approaches both on single and multi-object navigation tasks. Additional videos, code and the multi-object navigation benchmark will be available on https://finnbsch.github.io/OneMap.

Game theory is a powerful framework for reasoning about strategic interactions, with applications in domains ranging from day-to-day life to international politics. However, applying formal reasoning tools in such contexts is challenging, as these scenarios are often expressed in natural language. To address this, we introduce a framework for the autoformalization of game-theoretic scenarios, which translates natural language descriptions into formal logic representations suitable for formal solvers. Our approach utilizes one-shot prompting and a solver that provides feedback on syntactic correctness to allow LLMs to refine the code. We evaluate the framework using GPT-4o and a dataset of natural language problem descriptions, achieving 98% syntactic correctness and 88% semantic correctness. These results show the potential of LLMs to bridge the gap between real-life strategic interactions and formal reasoning.

Chain-of-thought prompting significantly boosts the reasoning ability of large language models but still faces three issues: hallucination problem, restricted interpretability, and uncontrollable generation. To address these challenges, we present AgentCOT, a llm-based autonomous agent framework, which can solve complex problems in an agent-style manner by multiple round LLM generation. At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence. In addition, we integrate the step's index into the reasoning process to form a graph structure for complex inference logic. We introduce two new strategies to enhance the performance of AgentCOT.We conduct extensive experiments to verify the effectiveness of our method on six common benchmarks. Results exhibit that our method brings in substantial improvements over current competitive approaches.

Large Language Model can reasonably understand and generate human expressions but may lack of thorough thinking and reasoning mechanisms. Recently there have been several studies which enhance the thinking ability of language models but most of them are not data-driven or training-based. In this paper, we are motivated by the cognitive mechanism in the natural world, and design a novel model architecture called TaS which allows it to first consider the thoughts and then express the response based upon the query. We design several pipelines to annotate or generate the thought contents from prompt-response samples, then add language heads in a middle layer which behaves as the thinking layer. We train the language model by the thoughts-augmented data and successfully let the thinking layer automatically generate reasonable thoughts and finally output more reasonable responses. Both qualitative examples and quantitative results validate the effectiveness and performance of TaS. Our code is available at https://anonymous.4open.science/r/TadE.