Retrieval or Global Context Understanding? On Many-Shot In-Context Learning for Long-Context Evaluation

Language models (LMs) have demonstrated an improved capacity to handle long-context information, yet existing long-context benchmarks primarily measure LMs' retrieval abilities with extended inputs, e.g., pinpointing a short phrase from long-form text. Therefore, they may fall short when evaluating models' global context understanding capacity, such as synthesizing and reasoning over content across input to generate the response. In this paper, we study long-context language model (LCLM) evaluation through many-shot in-context learning (ICL). Concretely, we identify the skills each ICL task requires, and examine models' long-context capabilities on them. We first ask: What types of ICL tasks benefit from additional demonstrations, and are these tasks effective at evaluating LCLMs? We find that classification and summarization tasks show notable performance improvements with additional demonstrations, while translation and reasoning tasks do not exhibit clear trends. This suggests the classification tasks predominantly test models' retrieval skills. Next, we ask: To what extent does each task require retrieval skills versus global context understanding from LCLMs? We develop metrics to categorize ICL tasks into two groups: (i) retrieval tasks that require strong retrieval ability to pinpoint relevant examples, and (ii) global context understanding tasks that necessitate a deeper comprehension of the full input. We find that not all datasets can effectively evaluate these long-context capabilities. To address this gap, we introduce a new many-shot ICL benchmark, MANYICLBENCH, designed to characterize LCLMs' retrieval and global context understanding capabilities separately. Benchmarking 11 open-weight LCLMs with MANYICLBENCH, we find that while state-of-the-art models perform well in retrieval tasks up to 64k tokens, many show significant drops in global context tasks at just 16k tokens.

RuAG: Learned-rule-augmented Generation for Large Language Models

In-context learning (ICL) and Retrieval-Augmented Generation (RAG) have gained attention for their ability to enhance LLMs' reasoning by incorporating external knowledge but suffer from limited contextual window size, leading to insufficient information injection. To this end, we propose a novel framework, RuAG, to automatically distill large volumes of offline data into interpretable first-order logic rules, which are injected into LLMs to boost their reasoning capabilities. Our method begins by formulating the search process relying on LLMs' commonsense, where LLMs automatically define head and body predicates. Then, RuAG applies Monte Carlo Tree Search (MCTS) to address the combinational searching space and efficiently discover logic rules from data. The resulting logic rules are translated into natural language, allowing targeted knowledge injection and seamless integration into LLM prompts for LLM's downstream task reasoning. We evaluate our framework on public and private industrial tasks, including natural language processing, time-series, decision-making, and industrial tasks, demonstrating its effectiveness in enhancing LLM's capability over diverse tasks.

Token-level Proximal Policy Optimization for Query Generation

Query generation is a critical task for web search engines (e.g. Google, Bing) and recommendation systems. Recently, state-of-the-art query generation methods leverage Large Language Models (LLMs) for their strong capabilities in context understanding and text generation. However, they still face challenges in generating high-quality queries in terms of inferring user intent based on their web search interaction history. In this paper, we propose Token-level Proximal Policy Optimization (TPPO), a noval approach designed to empower LLMs perform better in query generation through fine-tuning. TPPO is based on the Reinforcement Learning from AI Feedback (RLAIF) paradigm, consisting of a token-level reward model and a token-level proximal policy optimization module to address the sparse reward challenge in traditional RLAIF frameworks. To evaluate the effectiveness and robustness of TPPO, we conducted experiments on both open-source dataset and an industrial dataset that was collected from a globally-used search engine. The experimental results demonstrate that TPPO significantly improves the performance of query generation for LLMs and outperforms its existing competitors.

Self-Evolved Reward Learning for LLMs

Reinforcement Learning from Human Feedback (RLHF) is a crucial technique for aligning language models with human preferences, playing a pivotal role in the success of conversational models like GPT-4, ChatGPT, and Llama 2. A core challenge in employing RLHF lies in training a reliable reward model (RM), which relies on high-quality labels typically provided by human experts or advanced AI system. These methods can be costly and may introduce biases that affect the language model's responses. As language models improve, human input may become less effective in further enhancing their performance. In this paper, we propose Self-Evolved Reward Learning (SER), a novel approach where the RM generates additional training data to iteratively improve itself. We conducted extensive experiments on multiple datasets such as HH-RLHF and UltraFeedback, using models like Mistral and Llama 3, and compare SER against various baselines. Our results demonstrate that even with limited human-annotated data, learning from self-feedback can robustly enhance RM performance, thereby boosting the capabilities of large language models (LLMs).

FactBench: A Dynamic Benchmark for In-the-Wild Language Model Factuality Evaluation

Language models (LMs) are widely used by an increasing number of users, underscoring the challenge of maintaining factuality across a broad range of topics. We first present VERIFY (Verification and Evidence RetrIeval for FactualitY evaluation), a pipeline to evaluate LMs' factuality in real-world user interactions. VERIFY considers the verifiability of LM-generated content and categorizes content units as supported, unsupported, or undecidable based on the retrieved evidence from the Web. Importantly, factuality judgment by VERIFY correlates better with human evaluations than existing methods. Using VERIFY, we identify "hallucination prompts" across diverse topics, i.e., those eliciting the highest rates of incorrect and inconclusive LM responses. These prompts form FactBench, a dataset of 1K prompts across 150 fine-grained topics. Our dataset captures emerging factuality challenges in real-world LM interactions and can be regularly updated with new prompts. We benchmark widely-used LMs from GPT, Gemini, and Llama3.1 family on FactBench, yielding the following key findings: (i) Proprietary models exhibit better factuality, with performance declining from Easy to Hard hallucination prompts. (ii) Llama3.1-405B-Instruct shows comparable or lower factual accuracy than Llama3.1-70B-Instruct across all evaluation methods due to its higher subjectivity that leads to more content labeled as undecidable. (iii) Gemini1.5-Pro shows a significantly higher refusal rate, with over-refusal in 25% of cases. Our code and data are publicly available at https://huggingface.co/spaces/launch/factbench.

Deep Learning-Driven Microstructure Characterization and Vickers Hardness Prediction of Mg-Gd Alloys

In the field of materials science, exploring the relationship between composition, microstructure, and properties has long been a critical research focus. The mechanical performance of solid-solution Mg-Gd alloys is significantly influenced by Gd content, dendritic structures, and the presence of secondary phases. To better analyze and predict the impact of these factors, this study proposes a multimodal fusion learning framework based on image processing and deep learning techniques. This framework integrates both elemental composition and microstructural features to accurately predict the Vickers hardness of solid-solution Mg-Gd alloys. Initially, deep learning methods were employed to extract microstructural information from a variety of solid-solution Mg-Gd alloy images obtained from literature and experiments. This provided precise grain size and secondary phase microstructural features for performance prediction tasks. Subsequently, these quantitative analysis results were combined with Gd content information to construct a performance prediction dataset. Finally, a regression model based on the Transformer architecture was used to predict the Vickers hardness of Mg-Gd alloys. The experimental results indicate that the Transformer model performs best in terms of prediction accuracy, achieving an R^2 value of 0.9. Additionally, SHAP analysis identified critical values for four key features affecting the Vickers hardness of Mg-Gd alloys, providing valuable guidance for alloy design. These findings not only enhance the understanding of alloy performance but also offer theoretical support for future material design and optimization.

Expanding Chatbot Knowledge in Customer Service: Context-Aware Similar Question Generation Using Large Language Models

Reliable responses of service chatbots are often achieved by employing retrieval-based methods that restrict answers to a knowledge base comprising predefined question-answer pairs (QA pairs). To accommodate potential variations in how a customer's query may be expressed, it emerges as the favored solution to augment these QA pairs with similar questions that are possibly diverse while remaining semantic consistency. This augmentation task is known as Similar Question Generation (SQG). Traditional methods that heavily rely on human efforts or rule-based techniques suffer from limited diversity or significant semantic deviation from the source question, only capable of producing a finite number of useful questions. To address these limitations, we propose an SQG approach based on Large Language Models (LLMs), capable of producing a substantial number of diverse questions while maintaining semantic consistency to the source QA pair. This is achieved by leveraging LLMs' natural language understanding capability through fine-tuning with specially designed prompts. The experiments conducted on a real customer-service dataset demonstrate that our method surpasses baseline methods by a significant margin in terms of semantic diversity. Human evaluation further confirms that integrating the answer that reflects the customer's intention is crucial for increasing the number of generated questions that meet business requirements.

Closing the Loop: Learning to Generate Writing Feedback via Language Model Simulated Student Revisions

Providing feedback is widely recognized as crucial for refining students' writing skills. Recent advances in language models (LMs) have made it possible to automatically generate feedback that is actionable and well-aligned with human-specified attributes. However, it remains unclear whether the feedback generated by these models is truly effective in enhancing the quality of student revisions. Moreover, prompting LMs with a precise set of instructions to generate feedback is nontrivial due to the lack of consensus regarding the specific attributes that can lead to improved revising performance. To address these challenges, we propose PROF that PROduces Feedback via learning from LM simulated student revisions. PROF aims to iteratively optimize the feedback generator by directly maximizing the effectiveness of students' overall revising performance as simulated by LMs. Focusing on an economic essay assignment, we empirically test the efficacy of PROF and observe that our approach not only surpasses a variety of baseline methods in effectiveness of improving students' writing but also demonstrates enhanced pedagogical values, even though it was not explicitly trained for this aspect.

Narrative-of-Thought: Improving Temporal Reasoning of Large Language Models via Recounted Narratives

Reasoning about time and temporal relations is an integral aspect of human cognition, essential for perceiving the world and navigating our experiences. Though large language models (LLMs) have demonstrated impressive performance in many reasoning tasks, temporal reasoning remains challenging due to its intrinsic complexity. In this work, we first study an essential task of temporal reasoning -- temporal graph generation, to unveil LLMs' inherent, global reasoning capabilities. We show that this task presents great challenges even for the most powerful LLMs, such as GPT-3.5/4. We also notice a significant performance gap by small models (<10B) that lag behind LLMs by 50%. Next, we study how to close this gap with a budget constraint, e.g., not using model finetuning. We propose a new prompting technique tailored for temporal reasoning, Narrative-of-Thought (NoT), that first converts the events set to a Python class, then prompts a small model to generate a temporally grounded narrative, guiding the final generation of a temporal graph. Extensive experiments showcase the efficacy of NoT in improving various metrics. Notably, NoT attains the highest F1 on the Schema-11 evaluation set, while securing an overall F1 on par with GPT-3.5. NoT also achieves the best structural similarity across the board, even compared with GPT-3.5/4. Our code is available at https://github.com/launchnlp/NoT.

Scalable Fine-tuning from Multiple Data Sources:A First-Order Approximation Approach

We study the problem of fine-tuning a language model (LM) for a target task by optimally using the information from $n$ auxiliary tasks. This problem has broad applications in NLP, such as targeted instruction tuning and data selection in chain-of-thought fine-tuning. The key challenge of this problem is that not all auxiliary tasks are useful to improve the performance of the target task. Thus, choosing the right subset of auxiliary tasks is crucial. Conventional subset selection methods, such as forward & backward selection, are unsuitable for LM fine-tuning because they require repeated training on subsets of auxiliary tasks. This paper introduces a new algorithm to estimate model fine-tuning performances without repeated training. Our algorithm first performs multitask training using the data of all the tasks to obtain a meta initialization. Then, we approximate the model fine-tuning loss of a subset using functional values and gradients from the meta initialization. Empirically, we find that this gradient-based approximation holds with remarkable accuracy for twelve transformer-based LMs. Thus, we can now estimate fine-tuning performances on CPUs within a few seconds. We conduct extensive experiments to validate our approach, delivering a speedup of $30\times$ over conventional subset selection while incurring only $1\%$ error of the true fine-tuning performances. In downstream evaluations of instruction tuning and chain-of-thought fine-tuning, our approach improves over prior methods that utilize gradient or representation similarity for subset selection by up to $3.8\%$.