paperlist.ai

AI conference papers

AI conference paper library

Search papers from 30+ top conferences, including NeurIPS, ICLR, ICML, CVPR, ACL and AAAI. Filter by keyword, then open any paper for its abstract, authors and links.

arXiv

TempJail: Temporal Jailbreak Attack against Large Vision-Language Models via Subtitle Scheduling

Ling Zhou, Yihao Huang, Jingling sun, Zhiwen Tian, Yi Zeng, Qihe Liu, Shijie Zhou

Large vision-language models (LVLMs) have achieved remarkable progress in video understanding and reasoning. Despite extensive studies on text- and image-based jailbreaks, video jailbreaks against LVLMs remain largely unexplored. Existing video jailbreak methods mainly manipulate textual content embedded in videos, while overlooking how such information is organized over time. Our analysis reveals that jailbreak effectiveness depends not only on the semantics of textual information but also on its temporal presentation, including duration and timing-slot allocation. Motivated by this finding, we use subtitles, which are common in real-world videos and allow semantic content to be presented under precise temporal control without appearing visually intrusive, as a natural attack medium. Based on this insight, we propose TempJail, a black-box video-based jailbreak framework that constructs query-aligned dialogue-style subtitle sequences and optimizes their temporal scheduling to exploit temporal vulnerabilities in LVLMs and elicit responses that satisfy the harmful intent of the source query. Extensive experiments on four representative LVLMs and two datasets demonstrate that TempJail achieves the highest attack success rate across all evaluated model--dataset settings, outperforming the strongest baseline by 53 and 18 percentage points in dataset-averaged ASR on GPT-5 and Gemini 3.5-Flash, respectively.

arXiv

Projector Is All You Train

Nyx Iskandar, Saathvik Selvan, Slater Victoroff

The typical training process of a multimodal large language model (MLLM) involves adapting both the language model backbone and the projector between the backbone and a modality-specific encoder. We ask whether fine-tuning the backbone of an MLLM is necessary to adapt it to a new modality. Through experiments on 3D MLLMs, we find that training only the projector is sufficient to achieve strong multimodal performance relative to existing baseline models and our jointly trained MLLMs with the same encoder and backbone. We also show that joint training leads to undesirable drift in existing capabilities of the language model, which projector-only training avoids by definition. Furthermore, projector-only training has approximately twice the training sample throughput of joint training. We validate our findings across different language model backbones via 3D classification and captioning benchmarks as well as standard benchmarks evaluating language, vision, and spatial reasoning capabilities.

arXiv

StreamSoccer: Event-Driven Memory for Streaming Soccer Commentary

Chenxi Shao, Bozhong Wang, Jiaxin Huang, Zhao Liu, Sunwei Zhu, Tianxin Hang, Gaoqi He, Yang Li, Changbo Wang

Streaming video understanding requires models to causally update state as video arrives and organize growing history into semantic units that can evolve, persist, and be recalled under bounded computation and memory. This challenge is pronounced in live soccer commentary, where a system must describe completed events, summarize recent play, recall earlier events, or remain silent using only information available before each utterance. We present StreamSoccer, an event-driven system that uses event memory as its intermediate representation. A fixed-budget active memory integrates the stream; completed event states are retained locally and consolidated into retrievable historical records. A unified generator uses current, recent, and historical context to produce three commentary modes, while a rule-assisted scheduler selects a mode or silence. Unlike streaming video-language models organized around frames, visual tokens, or caches, and soccer-commentary methods based on predefined clips or output timestamps, StreamSoccer explicitly models event lifecycles. We construct a three-track streaming soccer commentary dataset and a layered evaluation protocol. At common reference anchors, StreamSoccer obtains CIDEr scores of 38.62, 23.96, and 17.39 for current-event, recent-window, and historical-memory commentary, ranking first on the current-event and historical-memory tracks and second on recent-window. Controlled ablations show that local completed events improve all tracks and that the full system performs best on all three. Across 174 raw-video runs on 58 matches, per-minute RTF p95 ranges from 0.10 to 0.22 without sustained growth with match history. These results indicate that event memory supports streaming soccer commentary across temporal scopes while controlling long-history computation.

arXiv

The Asymmetric Harms of LLM Compression

Yuan Wu, Mairui Li, Lesia Semenova, Chudi Zhong

Large language models (LLMs) compression reduces deployment costs, but standard aggregate metrics like perplexity and accuracy often mask underlying behavioral shifts. In this work, we systematically evaluate 3 LLMs across 11 compression methods to investigate the effects of compression on knowledge retention, model confidence, and social bias. We find that compression disproportionately reduces the relative retention of head knowledge compared to tail knowledge. Furthermore, compressed models often remain substantially confident in their incorrect answers on newly lost knowledge. Finally, we demonstrate that stable aggregate bias scores can conceal substantial, opposing shifts in stereotypical preferences across demographic subgroups. Together, these findings reveal asymmetric behavioral changes that aggregate performance measures fail to capture, highlighting the need for granular evaluation of compressed models before deployment.

arXiv

ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents

Yichu Fang, Sitong Wei, Haozhe Hu, Xiaoyu Shen

Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard prefix caching from reusing their key--value (KV) states. We introduce \textbf{ReCache}, a framework for independently caching resource representations while reducing their inference-time computational and memory overhead. Resource-wise attention removes cross-resource interactions and assigns resource-local positions, producing composition-invariant KV blocks. ReCache then restricts resource visibility to contribution-selected layer--KV-head-group routes and retains only invocation-critical fields through structural and semantic pruning. We evaluate ReCache on a benchmark assembled from seven public tool- and skill-use datasets, including resource-disjoint tests. Resource-wise attention matches dense invocation performance (82.3\% versus 82.4\% Inv-F1) while providing a 3.655$\times$ time-to-first-token speedup. The complete framework reduces allocated KV-tensor memory by 92.43\% and accelerates attention by 1.423$\times$. These results show that separating reusable schema encoding from selective resource access substantially reduces agentic inference costs with limited effectiveness loss. The code is available at https://github.com/EIT-NLP/ReCache.

arXiv

Can Agent Memory Systems Track Evolving State?

Xinyi Fan, Miri Liu, Ruozhen Yang, Siru Ouyang, Jiawei Han

As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps. While existing memory benchmarks focus largely on recall-shaped tasks, we argue an effective memory system must track the evolving state of the world; as facts, constraints, and decisions are revised over a long interaction, answers must reflect the current state and not a superseded one. We define this capability as state tracking and instantiate it in StateMemBench, a benchmark of 234 multi-session scenarios spanning two conversation-length regimes. Its closed-pool grading scores whether an answer reflects the current state, the superseded state, or fails otherwise, separating state-tracking failures from other errors by construction. Our analysis shows that this task is challenging for existing memory systems, retrieval-augmented baselines, and long-context baselines. We then present StateMem, a state-first memory method that explicitly tracks supersession and relational dependencies, and show it improves current-state accuracy over the strongest same-backbone baseline by 1.8x (0.205 -> 0.363) on DeepSeek-V4-Flash and over the strongest memory system by 1.6x (0.149 -> 0.233) on Qwen-3.5-9B, while remaining competitive with the long-context baselines. Finally, we show the same state approach can be applied as a lightweight single-call wrapper over existing memory systems, lifting current-state accuracy by +32 to +67 points on StateMemBench across six memory and retrieval backends. A length- and cost-matched control attributes +15 to +32 of those points to state structure rather than added context.

arXiv

Forking Fast: Efficiently Estimating Uncertainty Dynamics in Text Generation

Eric Bigelow, Amir Zur, Satchel Grant, Tal Haklay, Can Rager, Owen Lewis, Thomas McGrath, Jack Merullo, Ekdeep Singh Lubana, Atticus Geiger

LLM reasoning is stochastic, and so understanding a model requires grappling with the distribution of reasoning chains that it might produce for a given question, i.e., its uncertainty. Resampling-based analyses characterize this distribution, revealing which steps of a rollout determine how the model arrives at its answer. However, a major limitation of these approaches is that resampling text sequences at every token or sentence in a reasoning chain is very costly. Our work strives to make resampling analysis more computationally efficient, while also shedding light on an important scientific question: what is the right statistical model for explaining uncertainty dynamics in text generation? We show that when resampling many reasoning chains, uncertainty dynamics converge to stable patterns, and noise is largely an artifact of sampling rather than an LLM's sensitivity to each individual token or reasoning step. We develop a statistical model for smoothing noisy low-sample rollout data to better approximate high-sample data, allowing us to significantly cut sampling costs.

arXiv

PEA-DPO: Perception-Enhanced Alignment Direct Preference Optimization for MLLMs Alignment

Jiawei Feng, Jiancan Wu, Xingyu Zhu, Junkang Wu, Xiang Wang, Xiangnan He

Direct Preference Optimization (DPO) has emerged as an effective approach for aligning large language models (LLMs) with human preferences. However, its adaptation to multimodal settings remains unexplored. Through representational analysis, we identify a key limitation in multimodal preference optimization, which we term visual insensitivity: models often fail to distinguish between images and those with critical visual context removed. Our theoretical analysis further uncovers two manifestations of this problem, namely Across-Image Insensitivity and Within-Image Insensitivity. To address these challenges, we propose Perception-Enhanced Alignment DPO (PEA-DPO), a framework for multimodal LLMs alignment, which explicitly leverages visual preference signals to overcome visual insensitivity. We further provide a theoretical analysis demonstrating that PEA-DPO provably mitigates both failure modes. Empirical results demonstrate that PEA-DPO enhances sensitivity to visual context while preserving the language modeling capacity of the base model. Evaluations across three hallucination benchmarks using MLLMs of varying scales show that PEA-DPO effectively mitigates visual insensitivity, achieves stronger multimodal alignment, and substantially reduces hallucinations.

arXiv

Remember, Verify, or Ask? Cross-Family Evaluation of Memory Commitment in LLM Agents

Baichuan Li, Junyi Yao, Zihao Zheng

Persistent memory can personalize an LLM agent, but an incorrect durable update can silently distort future behavior. We study the memory-clarification boundary: whether interaction-derived information should be persisted, used only in the current context, re-verified, or clarified with the user. MCB contains 140 primary scenarios, split into 70 development and 70 held-out items, plus a separate 70-item contrast set. It evaluates both action labels and structured tool-call selection. Two non-authors independently label the 70 held-out primary and 70 contrast items (97.1% agreement, Cohen's kappa = 0.962); a blind third resolves four disagreements, replacing eight author labels by non-author majority. Across Claude and Qwen, models verify changing facts more reliably than they ask users to resolve ambiguity. Bare Qwen asks on 0/12 clarification items while verifying 12/18 freshness items. Few-shot prompting raises accuracy from 0.557 to 0.771 (paired delta = +0.214, Holm-adjusted exact McNemar p_H = 0.002), yet clarification recall remains 0.333. The policy prompt reduces erroneous persistence from 0.243 to 0.100 (p_H = 0.038), although its accuracy gain is not significant. Label-tool agreement is 57% for each Claude model and 23% for Qwen; Qwen accuracy falls from 0.557 to 0.343 (p_H = 0.047). Memory evaluation must test both stated decisions and tool-call choices.

arXiv

Reliable Financial Named Entity Recognition Under Domain Shift: Confidence Estimation and Selective Prediction

Zihao Zheng, Baichuan Li, Junyi Yao, Jiayu Long

Financial AI systems often train information extractors on one textual register and deploy them across filings, news, and user-generated content, and standard F1 scores do not indicate which predictions remain safe to automate when that input distribution changes. We study confidence estimation and selective prediction for financial named entity recognition (NER) on a three-tier stress test spanning SEC filings, financial news, and general-topic social media as an extreme out-of-domain condition, evaluating a BERT tagger and LoRA-tuned Qwen2.5-0.5B/1.5B models with five inference-time confidence signals, three training seeds, and bootstrap intervals. Confidence rankings themselves change under shift: whole-output probability is the strongest in-domain error detector but deteriorates out of domain, whereas entity-span probability and self-consistency are more robust; self-consistency is also better calibrated without post-hoc fitting. Abstention reduces sentence error from 34.3% to below 2% on the highest-confidence 40% of in-domain inputs and remains useful on financial news, but recovers no usefully large clean subset under the extreme social-media shift. These results motivate a staged deployment strategy that detects severe distribution shift upstream before applying prediction-level confidence gating.

arXiv

Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems

Mikio Nakano, Kazunori Komatani, Hironori Takeuchi

This paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be useful in various scenarios, like other dialogue systems, testing them with human users requires significant effort and cost. Therefore, testing with user simulators can be beneficial. Since most conventional user simulators have been primarily designed for training task-oriented dialogue systems, little attention has been paid to the personas of the simulated users. During development, testing interview dialogue systems requires simulating a wide range of user behaviors, but manually creating a large number of personas is labor-intensive. We propose a method that automatically generates personas for user simulators using a large language model. Furthermore, by assigning personality traits related to communication styles when generating personas, we aim to increase the diversity of communication styles in the user simulator. Experimental results show that the proposed method enables the user simulator to generate utterances with greater variation.

arXiv

From Retrieved Context to Runtime Control: Adaptive Compression for Edge-based RAG

Zlatan Feric, Amir Taherin, Yanzhi Wang, David Kaeli

Retrieval-augmented generation (RAG) improves language-model responses by grounding generation in external passages, which comes with overhead: retrieved context lengthens the prompt, increasing prefill work, KV-cache footprint, memory traffic, latency, and energy. Context compression offers a natural remedy by pruning retrieved text before generation. However, state-of-the-art context-compression methods are typically used with a fixed compression budget, or with the rate selected offline and then applied at inference time. This static view ignores both workload variation and the live state of the edge device. On an edge SoC, compression is not free: the compressor itself runs on the same SoC and consumes latency and energy that can offset any generation savings. This paper proposes a vision for telemetry-informed adaptive compression in edge RAG, grounded in experimental evidence. We characterize the compression tradeoff on the NVIDIA Jetson AGX Thor using Llama and Qwen generators, Natural Questions and HotpotQA datasets, and LLMLingua-2 compression. Our measurements show that generation dominates the RAG budget for larger models, reaching roughly 90% of per-query latency and 91% of GPU energy for 7B-8B generators. Exploring the impact of the compression rate reveals an adaptive operating region: mild compression can miss energy opportunities, and overly aggressive compression can hurt inference quality. Intermediate compression can reduce GPU energy by up to 53.2%, and SoC energy by up to 48.2%, with negligible quality loss. We argue for runtime policies that dynamically manage compression, guided by workload features and edge telemetry.

arXiv

When Machines Speak: A Unified Generative Framework for Integrating Machine-Native Symbols into Pretrained Large Language Models

Su Yan, Rakesh Iyer

Many real-world AI systems represent entities, behaviors, and structured information using discrete machine-native symbols rather than natural language. While these representations are compact and preserve task-relevant structure, they lie outside the linguistic token space of pretrained large language models (LLMs), creating a fundamental divide between language modeling and structured prediction. We introduce UniLang, a unified generative framework that bridges this divide by extending pretrained LLMs to treat machine-native symbols as first-class generative units alongside natural-language tokens. UniLang expands the LLM's vocabulary and embedding space with grounded machine-native representations, enabling textual and symbolic tokens to be jointly modeled and generated under a single autoregressive objective. This unified interface allows pretrained LLMs to directly operate on machine-native representations without requiring them to be verbalized as natural language or relying on task-specific architectures. We evaluate UniLang on two structurally distinct tasks, sequential recommendation and legal precedent prediction, spanning different domains and types of structured prediction. Across both tasks, UniLang consistently outperforms strong baselines, demonstrating a path toward extending pretrained LLMs beyond language and using them as a common generative modeling backbone for heterogeneous machine-native representations.

arXiv

Does Listening Matter? Backchanneling and Nodding in AI Clone

Koji Inoue, Kazushi Kato, Tatsuya Kawahara, Shunichi Kasahara

AI clones that imitate a specific person typically reproduce what the person says and how they sound, but not how they listen. We investigate whether adding multimodal listening behaviors gives such a clone more presence and authenticity. We integrated verbal backchannels and head nodding, driven by real-time prediction models, into an AI clone equipped with voice cloning and LLM-based responses. In a within-subjects study (N=35), adding these behaviors significantly improved the perceived attentiveness of the avatar, the sense of talking with the real person, and the feeling of co-presence. These results indicate that AI clone fidelity should extend beyond voice and response content to include interactive listening behavior.

arXiv

Automated Summarization of Financial News Using Large Language Models and Retrieval-Augmented Generation: An Early Empirical Study (Fall 2023)

Pranav Chandaliya

Stock market analysts and investors face a daily challenge: too much financial news, too little time. Manually reading and synthesizing hundreds of company-specific articles is impractical, yet missing key information can directly affect investment decisions. This project, conducted at George Washington University in Fall 2023, explores whether Large Language Models can automate this process reliably. We built a pipeline that pulls news articles from the News API, company background from Wikipedia, and stock price data from Yahoo Finance for ten major companies (AAPL, MSFT, GOOGL, AMZN, META, TSLA, JPM, NVDA, WMT, DIS). Because LLMs cannot directly process numerical tables, we developed a simple but effective template that converts stock data into natural language narratives. We then tested two summarization approaches (Summarize Chains and Retrieval-Augmented Generation with FAISS) across three open-source models (Falcon-7B-Instruct, DistilBART-CNN-12-6, BART-Large-XSum) for news, and GPT (text-davinci-003) for stock summaries. Falcon-7B with Summarize Chains gave the best results, covering all news events accurately and coherently. RAG, while promising in theory, caused severe repetition in Falcon and hallucinated facts in BART-Large when k was large. Both LLM-based approaches outperformed a simple Lead-3 baseline on ROUGE-1. We also built a Streamlit dashboard for interactive stock visualization. The work was done in Fall 2023, before RAG-based financial tools became widespread, and the failure modes we document, particularly hallucination under RAG in smaller models, remain relevant today.

arXiv

Grading the Graders: Verification Autonomy Levels (L0-L5) for LLM Reasoning

Yajie Yin

Large language models (LLMs) are increasingly paired with verifiers (step checkers, self-consistency filters, tool-based fact checkers, formal proof assistants) that claim to detect the model's errors. Yet the verification literature uses the word "level" to mean at least five different things: verification granularity, concept abstraction, risk tier, system-stack layer, and the epistemic source of the ground truth. We propose Verification Autonomy Levels (VAL), a meta-standard that classifies any verification scheme along a single axis: where does the verification spec come from, and what does the verdict guarantee? VAL ranges from L0 (LLM self-declaration; no deterministic anchor) through L2 (objective ground truth; correctness only) to L3/L4 (decidable systems with single-property or domain-level completeness), with L5 impossible in the unrestricted case. Central to VAL is the completeness blind spot: substitution- and sampling-based verifiers can confirm that proposed candidates hold, but cannot prove that no candidate was missed. We further identify a dichotomy the literature has not stated: completeness is reachable only for formally specifiable properties, whereas empirical open-world verification (fact-checking, diagnosis) caps at anchored correctness (L2). We document this gap empirically across four domains (symbolic mathematics, behavior monitoring, medical diagnosis, and code generation, the last a reverse validation with predictions stated before evidence) and in the strongest formal-verification baseline in our survey, whose authors note the verifier focuses on the correctness of each step. We show the levels of granularity, concept hierarchy, risk, and system stack are orthogonal to VAL, resolving a systematic conflation across 17 surveyed papers. Code and full assessment are released as supplementary material.

arXiv

GreekBarRetrieval: A Benchmark for Greek Statutory Retrieval

Ernest Beta, Odysseas S. Chlapanis, Dimitrios Galanis, Ion Androutsopoulos

Statutory retrieval is necessary for citation-grounded legal question answering, but remains underexplored for Greek. We introduce GreekBarRetrieval, a public retrieval benchmark derived from, and complementing GreekBarBench, which did not include retrieval. The new benchmark comprises 283 bar-exam questions, each accompanied by the facts of the case it refers to, and 6,308 candidate statutory articles to retrieve from. Questions and facts are stated in everyday language, but need to be mapped to the formal terminology of statutes and their abstract legal concepts. A further complication is that not all of the case facts are relevant to each question of a case. Experimenting with three BM25 variants and nine dense retrievers, we find that vanilla dense retrieval far outperforms vanilla sparse retrieval in Recall@100. However, LLM-based query reformulation helps BM25 close that gap, while also improving dense retrieval. With a ten-round ReAct-like LLM reformulation loop that we introduce, BM25 improves further in Recall@100 and obtains the best nDCG and MAP scores of all tested retrievers. Query reformulation also outperforms pseudo-relevance feedback, sparse-dense fusion, and English translation.

arXiv

Compress and Forget: bitsandbytes Quantization Amplifies Proactive Interference in LLMs

Shayan Shahrabi-Farahani, Dara Rahmati

Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior overwrites accumulate, mirroring a classical phenomenon in human working memory. Post-training quantization (PTQ) is now the default deployment path for open-weight models, yet its effect on this failure mode has not been tested. We evaluate three precision levels (FP16, INT8, INT4/NF4, via bitsandbytes) across three architecturally distinct instruction-tuned models (Qwen2.5-7B-Instruct, Mistral-7B-Instruct-v0.3, Phi-3.5-mini-instruct), holding the retrieval task fixed. INT4 quantization significantly reduces accuracy under high interference in every model (e.g., from 81.0% to 68.3% for Qwen), confirmed by paired McNemar's tests ($p \le 2.6 \times 10^{-6}$) and a mixed-effects regression spanning all interference levels; INT8, often assumed safe, also carries a smaller but real penalty in two of three models. The effect is specific to semantically similar (word-type) distractors and reverses sign under a numeric control condition, and is mechanistically linked to a rise in same-key intrusion errors under INT4 (from 21.5% to 24.6% of trials, $p = 4.8 \times 10^{-7}$). A follow-up ablation shows the effect originates in the quantized transformer backbone rather than the output projection layer. These results suggest that bitsandbytes 4-bit quantization can impose an additional cost on applications relying on long, updatable, semantically dense contexts, even when aggregate benchmark accuracy appears largely unaffected. We release our code and tokenizer-verified vocabulary construction method at https://github.com/ShayanShahrabi/compress-and-forget

arXiv

Language Has Two Parameters: Narrative-Induced Semantic Plasticity and Phase-Sensitive Interpretation

Hollis Robbins

Reading fiction or encountering narrative generally does not merely add information. The encounter changes the reader. This paper proposes that encounters alter persistent relations among simultaneously active meanings, producing individual and shared histories that population-trained language models do not necessarily retain. A model may be told of an encounter and reproduce its consequences while the history remains in context; this is not the same as being changed by the encounter. This paper formalizes this missing relational state as phase, sets out testable predictions about encounter order, quotation, and suppressed meanings, and argues that future AI agents will need persistent semantic states indexed to particular individuals and relationships. The matching risk is semantic poisoning: an attack that re-signs relations among meanings already present.

arXiv

Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation

Cedar Site Bai, Zhenyu Liao, Duanshun Li, Sheikh Sarwar, Huiyuan Chen, Yuan Chen, Changhe Yuan, Haiyang Zhang, Qilin Qi

Recent advances in large language models (LLMs) have enabled their use as conversational recommender systems (CRS), demonstrating strong recommendation accuracy and natural dialogue. However, guiding multi-turn interactions to elicit user preferences effectively remains challenging. Existing approaches either use separate reinforcement learning agents with templated interactions or optimize for interactivity judged by another LLM, without measuring how much useful information is actually gained. We propose a new approach that quantifies the effectiveness of each interaction by the reduction in the assistant's uncertainty, measured via entropy over recommendations. We apply this entropy reduction as a reward---without relying on ground-truth recommendations, which are often unavailable in real-world scenarios---to fine-tune the LLM, enabling strategic interaction generation. Empirical results with supervised fine-tuning (SFT) and direct preference optimization (DPO) on the INSPIRED and ReDial datasets show that our method improves both recommendation quality and conversational efficiency.

Keep browsing

More papers from top AI conferences

30+ top conferences, by conference, year, and topic.