Retrieved documents containing noise will hinder Retrieval-Augmented Generation (RAG) from detecting answer clues, necessitating noise filtering mechanisms to enhance accuracy. Existing methods use re-ranking or summarization to identify the most relevant sentences, but directly and accurately locating answer clues from these large-scale and complex documents remains challenging. Unlike these document-level operations, we treat noise filtering as a sentence-level MinMax optimization problem: first identifying the potential clues from multiple documents using contextual information, then ranking them by relevance, and finally retaining the least clues through truncation. In this paper, we propose FineFilter, a novel fine-grained noise filtering mechanism for RAG consisting of a clue extractor, a re-ranker, and a truncator. We optimize each module to tackle complex reasoning challenges: (1) Clue extractor firstly uses sentences containing the answer and similar ones as fine-tuned targets, aiming at extracting sufficient potential clues; (2) Re-ranker is trained to prioritize effective clues based on the real feedback from generation module, with clues capable of generating correct answer as positive samples and others as negative; (3) Truncator takes the minimum clues needed to answer the question (truncation point) as fine-tuned targets, and performs truncation on the re-ranked clues to achieve fine-grained noise filtering. Experiments on three QA datasets demonstrate that FineFilter significantly outperforms baselines in terms of performance and inference cost. Further analysis on each module shows the effectiveness of our optimizations for complex reasoning.

Fine-tuning significantly improves the performance of Large Language Models (LLMs), yet its underlying mechanisms remain poorly understood. This paper aims to provide an in-depth interpretation of the fine-tuning process through circuit analysis, a popular tool in Mechanistic Interpretability (MI). Unlike previous studies \cite{prakash2024finetuningenhancesexistingmechanisms,chhabra2024neuroplasticity} that focus on tasks where pre-trained models already perform well, we develop a set of mathematical tasks where fine-tuning yields substantial performance gains, which are closer to the practical setting. In our experiments, we identify circuits at various checkpoints during fine-tuning and examine the interplay between circuit analysis, fine-tuning methods, and task complexities. First, we find that while circuits maintain high node similarity before and after fine-tuning, their edges undergo significant changes, which is in contrast to the previous work \cite{prakash2024finetuningenhancesexistingmechanisms,chhabra2024neuroplasticity} that show circuits only add some additional components after fine-tuning. Based on these observations, we develop a circuit-aware Low-Rank Adaptation (LoRA) method, which assigns ranks to layers based on edge changes in the circuits. Experimental results demonstrate that our circuit-based LoRA algorithm achieves an average performance improvement of 2.46\% over standard LoRA with similar parameter sizes. Furthermore, we explore how combining circuits from subtasks can enhance fine-tuning in compositional tasks, providing new insights into the design of such tasks and deepening the understanding of circuit dynamics and fine-tuning mechanisms.

Knowledge Tracing (KT) aims to predict students' future performances based on their former exercises and additional information in educational settings. KT has received significant attention since it facilitates personalized experiences in educational situations. Simultaneously, the autoregressive modeling on the sequence of former exercises has been proven effective for this task. One of the primary challenges in autoregressive modeling for Knowledge Tracing is effectively representing the anterior (pre-response) and posterior (post-response) states of learners across exercises. Existing methods often employ complex model architectures to update learner states using question and response records. In this study, we propose a novel perspective on knowledge tracing task by treating it as a generative process, consistent with the principles of autoregressive models. We demonstrate that knowledge states can be directly represented through autoregressive encodings on a question-response alternate sequence, where model generate the most probable representation in hidden state space by analyzing history interactions. This approach underpins our framework, termed Alternate Autoregressive Knowledge Tracing (AAKT). Additionally, we incorporate supplementary educational information, such as question-related skills, into our framework through an auxiliary task, and include extra exercise details, like response time, as additional inputs. Our proposed framework is implemented using advanced autoregressive technologies from Natural Language Generation (NLG) for both training and prediction. Empirical evaluations on four real-world KT datasets indicate that AAKT consistently outperforms all baseline models in terms of AUC, ACC, and RMSE. Furthermore, extensive ablation studies and visualized analysis validate the effectiveness of key components in AAKT.

Aspect-based sentiment analysis (ABSA) is a crucial task in information extraction and sentiment analysis, aiming to identify aspects with associated sentiment elements in text. However, existing ABSA datasets are predominantly English-centric, limiting the scope for multilingual evaluation and research. To bridge this gap, we present M-ABSA, a comprehensive dataset spanning 7 domains and 21 languages, making it the most extensive multilingual parallel dataset for ABSA to date. Our primary focus is on triplet extraction, which involves identifying aspect terms, aspect categories, and sentiment polarities. The dataset is constructed through an automatic translation process with human review to ensure quality. We perform extensive experiments using various baselines to assess performance and compatibility on M-ABSA. Our empirical findings highlight that the dataset enables diverse evaluation tasks, such as multilingual and multi-domain transfer learning, and large language model evaluation, underscoring its inclusivity and its potential to drive advancements in multilingual ABSA research.

This paper introduces Code-Vision, a benchmark designed to evaluate the logical understanding and code generation capabilities of Multimodal Large Language Models (MLLMs). It challenges MLLMs to generate a correct program that fulfills specific functionality requirements based on a given flowchart, which visually represents the desired algorithm or process. Code-Vision comprises three subsets: HumanEval-V, Algorithm, and MATH, which evaluate MLLMs' coding abilities across basic programming, algorithmic, and mathematical problem-solving domains. Our experiments evaluate 12 MLLMs on Code-Vision. Experimental results demonstrate that there is a large performance difference between proprietary and open-source models. On Hard problems, GPT-4o can achieve 79.3% pass@1, but the best open-source model only achieves 15%. Further experiments reveal that Code-Vision can pose unique challenges compared to other multimodal reasoning benchmarks MMCode and MathVista. We also explore the reason for the poor performance of the open-source models. All data and codes are available at https://github.com/wanghanbinpanda/CodeVision.

Large Language Models revolutionized NLP and showed dramatic performance improvements across several tasks. In this paper, we investigated the role of such language models in text classification and how they compare with other approaches relying on smaller pre-trained language models. Considering 32 datasets spanning 8 languages, we compared zero-shot classification, few-shot fine-tuning and synthetic data based classifiers with classifiers built using the complete human labeled dataset. Our results show that zero-shot approaches do well for sentiment classification, but are outperformed by other approaches for the rest of the tasks, and synthetic data sourced from multiple LLMs can build better classifiers than zero-shot open LLMs. We also see wide performance disparities across languages in all the classification scenarios. We expect that these findings would guide practitioners working on developing text classification systems across languages.

We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the violation-of-expectation framework, we find that video prediction models trained to predict outcomes in a learned representation space demonstrate an understanding of various intuitive physics properties, such as object permanence and shape consistency. In contrast, video prediction in pixel space and multimodal large language models, which reason through text, achieve performance closer to chance. Our comparisons of these architectures reveal that jointly learning an abstract representation space while predicting missing parts of sensory input, akin to predictive coding, is sufficient to acquire an understanding of intuitive physics, and that even models trained on one week of unique video achieve above chance performance. This challenges the idea that core knowledge -- a set of innate systems to help understand the world -- needs to be hardwired to develop an understanding of intuitive physics.

Large language models (LLMs) have recently been introduced to graph learning, aiming to extend their zero-shot generalization success to tasks where labeled graph data is scarce. Among these applications, inference over text-attributed graphs (TAGs) presents unique challenges: existing methods struggle with LLMs' limited context length for processing large node neighborhoods and the misalignment between node embeddings and the LLM token space. To address these issues, we establish two key principles for ensuring generalization and derive the framework LLM-BP accordingly: (1) Unifying the attribute space with task-adaptive embeddings, where we leverage LLM-based encoders and task-aware prompting to enhance generalization of the text attribute embeddings; (2) Developing a generalizable graph information aggregation mechanism, for which we adopt belief propagation with LLM-estimated parameters that adapt across graphs. Evaluations on 11 real-world TAG benchmarks demonstrate that LLM-BP significantly outperforms existing approaches, achieving 8.10% improvement with task-conditional embeddings and an additional 1.71% gain from adaptive aggregation.

Large Language Models (LLMs) are widely used as conversational agents, exploiting their capabilities in various sectors such as education, law, medicine, and more. However, LLMs are often subjected to context-shifting behaviour, resulting in a lack of consistent and interpretable personality-aligned interactions. Adherence to psychological traits lacks comprehensive analysis, especially in the case of dyadic (pairwise) conversations. We examine this challenge from two viewpoints, initially using two conversation agents to generate a discourse on a certain topic with an assigned personality from the OCEAN framework (Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism) as High/Low for each trait. This is followed by using multiple judge agents to infer the original traits assigned to explore prediction consistency, inter-model agreement, and alignment with the assigned personality. Our findings indicate that while LLMs can be guided toward personality-driven dialogue, their ability to maintain personality traits varies significantly depending on the combination of models and discourse settings. These inconsistencies emphasise the challenges in achieving stable and interpretable personality-aligned interactions in LLMs.

The automatic generation of programs has long been a fundamental challenge in computer science. Recent benchmarks have shown that large language models (LLMs) can effectively generate code at the function level, make code edits, and solve algorithmic coding tasks. However, to achieve full automation, LLMs should be able to generate production-quality, self-contained application modules. To evaluate the capabilities of LLMs in solving this challenge, we introduce BaxBench, a novel evaluation benchmark consisting of 392 tasks for the generation of backend applications. We focus on backends for three critical reasons: (i) they are practically relevant, building the core components of most modern web and cloud software, (ii) they are difficult to get right, requiring multiple functions and files to achieve the desired functionality, and (iii) they are security-critical, as they are exposed to untrusted third-parties, making secure solutions that prevent deployment-time attacks an imperative. BaxBench validates the functionality of the generated applications with comprehensive test cases, and assesses their security exposure by executing end-to-end exploits. Our experiments reveal key limitations of current LLMs in both functionality and security: (i) even the best model, OpenAI o1, achieves a mere 60% on code correctness; (ii) on average, we could successfully execute security exploits on more than half of the correct programs generated by each LLM; and (iii) in less popular backend frameworks, models further struggle to generate correct and secure applications. Progress on BaxBench signifies important steps towards autonomous and secure software development with LLMs.